[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6M9R9NPAAPHJBKVZJJR4PKC":3,"skill-same:01M6M9R9NPAAPHJBKVZJJR4PKC":167},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":56,"linkOnly":57,"markdownContent":58,"markdownBody":59,"frontMatter":60,"refName":82,"commitSha":83,"skillDirectory":84,"forksCount":85,"repositoryHtmlUrl":86,"repositoryHomepageUrl":87,"ownerHtmlUrl":88,"ownerBlogUrl":89,"ownerDescription":90,"updatedAt":91,"install":92,"resources":104},"01M6M9R9NPAAPHJBKVZJJR4PKC","autoskill",null,"Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing research-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https:\u002F\u002Fgithub.com\u002Fscreenpipe\u002Fscreenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[5,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55],"edit","drafting","for","daemon","port","chain","screen","recipes","false","authoring","local","do","observe","only","claude api","write","read","analyze","access","Bash","Composition","api","Workflow Automation","run","skill authoring","auth","workflows","workflow","ai agents","2026-11-10 10:12:30",false,"---\nname: autoskill\ndescription: Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing research-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https:\u002F\u002Fgithub.com\u002Fscreenpipe\u002Fscreenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.\nlicense: MIT\nallowed-tools: Read Write Edit Bash\nmetadata:\n  version: '1.4'\n  category: research-automation\n  maintainer: Kalaris Labs\n  openclaw:\n    requires:\n      bins:\n      - screenpipe\n    primaryEnv: SCREENPIPE_TOKEN\n    envVars:\n    - name: SCREENPIPE_TOKEN\n      required: true\n      description: Auth token for the local screenpipe daemon.\n    - name: ANTHROPIC_API_KEY\n      required: false\n      description: For Claude API calls during skill drafting.\n    - name: FOUNDRY_API_KEY\n      required: false\n      description: Optional Foundry access for drafting.\n  tags: skill authoring, workflow automation, research automation, AI agents\n---\n\n# autoskill\n\n> **Requires a running [screenpipe](https:\u002F\u002Fgithub.com\u002Fscreenpipe\u002Fscreenpipe) daemon.** This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default `http:\u002F\u002Flocalhost:3030`). If the daemon isn't running, `run()` raises `ScreenpipeUnreachable` with install instructions.\n\n> **Network access & environment variables.** This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of `http:\u002F\u002Flocalhost:1234\u002Fv1` (LM Studio, default), `https:\u002F\u002Fapi.anthropic.com` (opt-in Claude), or a user-supplied BYOK Foundry gateway. The skill reads three environment variables — `SCREENPIPE_TOKEN`, `ANTHROPIC_API_KEY`, `FOUNDRY_API_KEY` — and uses each only to authenticate to the single endpoint its name implies. No other network destinations, no telemetry, no data egress to any third party.\n\n## Overview\n\nTurn the user's own workflow history — captured passively by the local [screenpipe](https:\u002F\u002Fgithub.com\u002Fscreenpipe\u002Fscreenpipe) daemon — into new skills. This skill is on-demand: the user invokes it with a time window, it queries screenpipe's local HTTP API, clusters repeated workflow patterns, compares each pattern against the existing skills in this repo, and produces a staged folder of proposals the user can review, edit, and promote.\n\n## When to Use This Skill\n\nInvoke this skill when the user asks to:\n- \"Analyze my last 4 hours \u002F day \u002F week and propose new skills.\"\n- \"Look at what I've been doing and tell me what's not covered yet.\"\n- \"Draft a skill from my recent workflow.\"\n- \"Find composition recipes for workflows I repeat.\"\n\nDo **not** invoke it for one-off questions about screenpipe itself, for real-time screen queries, or without an explicit user request — the skill analyzes sensitive local content and must stay explicitly user-triggered.\n\n## Privacy Posture\n\n- **Screenpipe handles app\u002Fwindow filtering at capture time.** Install a starter deny-list by copying `references\u002Fscreenpipe-config.yaml` into the user's screenpipe config. Sensitive apps (password managers, messaging, banking) are never OCR'd in the first place.\n- **Raw OCR never leaves the machine.** `scripts\u002Ffetch_window.py` pulls data over localhost HTTP. `scripts\u002Fcluster.py` reduces the timeline to app\u002Fduration\u002Ftitle summaries. `scripts\u002Fredact.py` strips emails, API keys, bearer tokens, and phone numbers as defense-in-depth before any cluster summary reaches the LLM.\n- **LLM backend defaults to `local`.** The recommended setup is [LM Studio](https:\u002F\u002Flmstudio.ai\u002F) running `Gemma-4-31B-it` — strong reasoning at a size that fits on most workstation GPUs, and no data ever leaves your machine. Cloud backends (`claude`, `foundry`) are opt-in and documented in `config.yaml` for users who explicitly want them. Detection and embeddings always run locally regardless of backend choice.\n- **Dry-run mode** (`--plan`) prints the exact timeline that will be analyzed before any LLM call.\n- **TLS for localhost** (optional, for corporate policy): see `references\u002Fhttps-proxy.md` for the Caddy pattern.\n\n## Prerequisites\n\n### 1. Screenpipe daemon\n\nEither install the official release or build from source. Either way the daemon binds HTTP on `localhost:3030` by default.\n\n**From source** (recommended if you want the CLI daemon without the desktop GUI):\n\n```bash\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Fmediar-ai\u002Fscreenpipe.git\ncd screenpipe\ncargo build -p screenpipe-engine --release\n# System deps (macOS): cmake + full Xcode.app (not just Command Line Tools).\n#   brew install cmake\n#   # if xcodebuild plug-ins error: sudo xcodebuild -runFirstLaunch\n.\u002Ftarget\u002Frelease\u002Fscreenpipe doctor   # confirm permissions + ffmpeg\n.\u002Ftarget\u002Frelease\u002Fscreenpipe record --disable-audio --use-pii-removal\n```\n\nFirst run will prompt for macOS Screen Recording permission. Grant it and relaunch.\n\n### 2. Screenpipe API token\n\nThe local API now requires bearer auth. Retrieve your token and export it:\n\n```bash\nexport SCREENPIPE_TOKEN=$(screenpipe auth token)\n```\n\n(Or set `screenpipe.token` directly in `config.yaml` — env var is preferred since it keeps secrets out of version control.)\n\n### 3. Python environment\n\nVia `pipenv` from the repo root:\n\n```bash\npipenv install httpx pyyaml sentence-transformers\n```\n\nThe embedding model (`sentence-transformers\u002Fall-MiniLM-L6-v2`, ~80 MB) downloads on first run.\n\n### 4. Local LLM (default path) — LM Studio\n\n- Install [LM Studio](https:\u002F\u002Flmstudio.ai\u002F).\n- Download `Gemma-4-31B-it` (or another strong reasoning model; adjust `local.model` in `config.yaml`).\n- Load it via the CLI for headless use (no GUI required):\n\n```bash\nlms load gemma-4-31b-it --context-length 131072 --gpu max -y\nlms status   # confirm server running on :1234\n```\n\n### 5. Cloud LLM backends (optional, opt-in)\n\nOnly if you explicitly opt out of local:\n- `claude`: set `ANTHROPIC_API_KEY`, flip `backend: claude` in `config.yaml`.\n- `foundry`: set `FOUNDRY_API_KEY`, flip `backend: foundry`, set `foundry.endpoint` to your corporate gateway URL.\n\n## Architecture\n\n```\nscreenpipe daemon (user-installed)\n        │  HTTP on localhost:3030\n        ▼\nscripts\u002Ffetch_window.py    → normalized timeline events\nscripts\u002Fredact.py          → regex scrub (defense-in-depth)\nscripts\u002Fcluster.py         → sessions + clusters (local only)\nscripts\u002Fmatch_skills.py    → top-k vs existing 135 skills (local embeddings)\nscripts\u002Fsynthesize.py      → LLM judge: reuse \u002F compose \u002F novel\n        │\n        ▼\n~\u002F.autoskill\u002Fproposed\u002F\u003Ctimestamp>\u002F        (default; override with --out)\n  ├── report.md\n  ├── composition-recipes\u002F\u003Cname>\u002FSKILL.md\n  └── new-skills\u002F\u003Cname>\u002FSKILL.md\n\nscripts\u002Fpromote.py         → user-approved proposal → skills\u002F\u003Cname>\u002F\n```\n\n## Workflow\n\nThe skill ships a unified CLI at `scripts\u002Fautoskill.py` with three subcommands:\n\n```bash\npython scripts\u002Fautoskill.py doctor   --config config.yaml --skills-dir ..\u002F\npython scripts\u002Fautoskill.py run      --start ... --end ... --config config.yaml\npython scripts\u002Fautoskill.py promote  --proposed ~\u002F.autoskill\u002Fproposed\u002F\u003Cts> --skills-dir ..\u002F --name \u003Cskill>\n```\n\n### 0. Preflight with `doctor`\n\nBefore a full run, verify every dependency in one shot:\n\n```bash\npython scripts\u002Fautoskill.py doctor \\\n  --config skills\u002Fautoskill\u002Fconfig.yaml \\\n  --skills-dir skills\n```\n\nThe report covers `config` (backend choice valid), `skills_dir` (exists), `screenpipe` (reachable + authed), and `llm` (LM Studio serving or API key present). Non-zero exit on any failure, with the offending line marked `error`.\n\n### 1. Run the pipeline\n\n```bash\nexport SCREENPIPE_TOKEN=$(screenpipe auth token)\npython scripts\u002Fautoskill.py run \\\n  --start \"2026-04-17T00:00:00Z\" \\\n  --end   \"2026-04-17T23:59:59Z\" \\\n  --config skills\u002Fautoskill\u002Fconfig.yaml \\\n  --skills-dir skills\n```\n\nProposals land in `~\u002F.autoskill\u002Fproposed\u002F\u003Ctimestamp>\u002F` by default, keeping experimental output out of the skills repo. Pass `--out PATH` to override.\n\nInternally:\n1. **Fetch** — `fetch_window` paginates screenpipe's `\u002Fsearch` endpoint, normalizes events to `{ts, app, window_title, text, content_type}`.\n2. **Redact** — `redact` scrubs emails, API keys, bearer tokens, phones from OCR text and window titles as defense-in-depth over screenpipe's own PII removal.\n3. **Cluster** — `segment_sessions` splits on idle gaps (default 10 min) and drops short sessions; `cluster_sessions` groups sessions by app-signature and keeps clusters of size `min_cluster_size` (default 2).\n4. **Match** — `load_skill_descriptions` reads frontmatter from every `SKILL.md` in `skills\u002F`; `top_k_matches` ranks each cluster against all skills using local `sentence-transformers` embeddings (cosine similarity).\n5. **Synthesize** — `synthesize` prompts the configured LLM backend to classify each cluster as `reuse`, `compose`, or `novel` and emit a SKILL.md body where appropriate.\n6. **Report** — writes `\u003Cout_dir>\u002F\u003Cts>\u002Freport.md`, plus `new-skills\u002F\u003Cname>\u002FSKILL.md` or `composition-recipes\u002F\u003Cname>\u002FSKILL.md` for each proposal.\n\nAdd `--dry-run` to stop after clustering; this skips the LLM (and the sentence-transformers load), writing only `plan.md` for inspection.\n\n### 2. Review and promote\n\nOpen `~\u002F.autoskill\u002Fproposed\u002F\u003Cts>\u002Freport.md`, edit drafts in place, delete anything you don't want. Then:\n\n```bash\npython scripts\u002Fautoskill.py promote \\\n  --proposed ~\u002F.autoskill\u002Fproposed\u002F2026-04-17T14-30-00 \\\n  --skills-dir skills \\\n  --name zotero-pubmed-helper\n```\n\n`promote` moves the directory into `skills\u002F\u003Cname>\u002F`, refusing to overwrite an existing skill. Exits non-zero with a friendly error if the proposal isn't found or the target already exists.\n\n## Configuration\n\nSee `config.yaml` for the full shape. Default values (local-first):\n\n```yaml\nbackend: local\nlocal:\n  endpoint: http:\u002F\u002Flocalhost:1234\u002Fv1   # LM Studio's Developer server\n  model: Gemma-4-31B-it\n\nscreenpipe:\n  url: http:\u002F\u002Flocalhost:3030           # or https:\u002F\u002Fscreenpipe.local via Caddy\n\ncluster:\n  min_session_minutes: 5\n  idle_gap_minutes: 10\n  min_cluster_size: 2\n```\n\nTo opt into a cloud backend:\n\n```yaml\nbackend: claude                         # or foundry\nclaude:\n  model: claude-opus-4-7\n```\n\n## Composition recipes vs new skills\n\n- **compose**: the LLM judged that chaining existing skills covers the workflow. The emitted SKILL.md is intentionally thin — frontmatter + a \"Workflow\" section that invokes existing skills in order. The same agent runtime that discovered the skill can then invoke it end-to-end.\n- **novel**: no combination of existing skills covers it. A fuller SKILL.md is drafted, still following repo conventions (frontmatter, Overview, When to Use, Workflow). The user should always review new-skill drafts before promoting.\n\n## Testing\n\nThe skill is covered by a small pytest suite at `tests\u002Fautoskill\u002F` in the repository root. Each script is unit-tested in isolation with dependency injection (mock HTTP transport, stub backend, stub embedder):\n\n```bash\npython -m pytest tests\u002Fautoskill -v\n```\n\n## Composition with other skills in this repo\n\nThe autoskill's embedding index covers all 135 sibling skills. Workflows that look like scientific writing will match `scientific-writing` \u002F `literature-review` \u002F `citation-management`; figure work will match `scientific-schematics` \u002F `generate-image` \u002F `infographics`; slide prep matches `scientific-slides` \u002F `pptx`; etc. When a cluster scores high against two or three sibling skills the emitted composition recipe names them explicitly, so the user's future agent invocations use the optimized paths already documented in this repo.\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the objective, evaluation metric, budget (time, compute, money) and stopping criteria.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Run one iteration end to end and inspect logs before scaling up.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Evaluate on held-out data; keep an audit trail of every iteration, hypothesis and result.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| An iteration produces suspiciously large gains | Check for leakage or evaluation bugs before accepting the result. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Record negative results; never select or report only favourable runs.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `research-skill-creator`: Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet…\n","# autoskill\n\n> **Requires a running [screenpipe](https:\u002F\u002Fgithub.com\u002Fscreenpipe\u002Fscreenpipe) daemon.** This skill has no alternate data source — it reads exclusively from the local screenpipe HTTP API (default `http:\u002F\u002Flocalhost:3030`). If the daemon isn't running, `run()` raises `ScreenpipeUnreachable` with install instructions.\n\n> **Network access & environment variables.** This skill makes authenticated HTTP requests to (a) the user's local screenpipe daemon on loopback, and (b) the user-configured LLM backend — one of `http:\u002F\u002Flocalhost:1234\u002Fv1` (LM Studio, default), `https:\u002F\u002Fapi.anthropic.com` (opt-in Claude), or a user-supplied BYOK Foundry gateway. The skill reads three environment variables — `SCREENPIPE_TOKEN`, `ANTHROPIC_API_KEY`, `FOUNDRY_API_KEY` — and uses each only to authenticate to the single endpoint its name implies. No other network destinations, no telemetry, no data egress to any third party.\n\n## Overview\n\nTurn the user's own workflow history — captured passively by the local [screenpipe](https:\u002F\u002Fgithub.com\u002Fscreenpipe\u002Fscreenpipe) daemon — into new skills. This skill is on-demand: the user invokes it with a time window, it queries screenpipe's local HTTP API, clusters repeated workflow patterns, compares each pattern against the existing skills in this repo, and produces a staged folder of proposals the user can review, edit, and promote.\n\n## When to Use This Skill\n\nInvoke this skill when the user asks to:\n- \"Analyze my last 4 hours \u002F day \u002F week and propose new skills.\"\n- \"Look at what I've been doing and tell me what's not covered yet.\"\n- \"Draft a skill from my recent workflow.\"\n- \"Find composition recipes for workflows I repeat.\"\n\nDo **not** invoke it for one-off questions about screenpipe itself, for real-time screen queries, or without an explicit user request — the skill analyzes sensitive local content and must stay explicitly user-triggered.\n\n## Privacy Posture\n\n- **Screenpipe handles app\u002Fwindow filtering at capture time.** Install a starter deny-list by copying `references\u002Fscreenpipe-config.yaml` into the user's screenpipe config. Sensitive apps (password managers, messaging, banking) are never OCR'd in the first place.\n- **Raw OCR never leaves the machine.** `scripts\u002Ffetch_window.py` pulls data over localhost HTTP. `scripts\u002Fcluster.py` reduces the timeline to app\u002Fduration\u002Ftitle summaries. `scripts\u002Fredact.py` strips emails, API keys, bearer tokens, and phone numbers as defense-in-depth before any cluster summary reaches the LLM.\n- **LLM backend defaults to `local`.** The recommended setup is [LM Studio](https:\u002F\u002Flmstudio.ai\u002F) running `Gemma-4-31B-it` — strong reasoning at a size that fits on most workstation GPUs, and no data ever leaves your machine. Cloud backends (`claude`, `foundry`) are opt-in and documented in `config.yaml` for users who explicitly want them. Detection and embeddings always run locally regardless of backend choice.\n- **Dry-run mode** (`--plan`) prints the exact timeline that will be analyzed before any LLM call.\n- **TLS for localhost** (optional, for corporate policy): see `references\u002Fhttps-proxy.md` for the Caddy pattern.\n\n## Prerequisites\n\n### 1. Screenpipe daemon\n\nEither install the official release or build from source. Either way the daemon binds HTTP on `localhost:3030` by default.\n\n**From source** (recommended if you want the CLI daemon without the desktop GUI):\n\n```bash\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Fmediar-ai\u002Fscreenpipe.git\ncd screenpipe\ncargo build -p screenpipe-engine --release\n# System deps (macOS): cmake + full Xcode.app (not just Command Line Tools).\n#   brew install cmake\n#   # if xcodebuild plug-ins error: sudo xcodebuild -runFirstLaunch\n.\u002Ftarget\u002Frelease\u002Fscreenpipe doctor   # confirm permissions + ffmpeg\n.\u002Ftarget\u002Frelease\u002Fscreenpipe record --disable-audio --use-pii-removal\n```\n\nFirst run will prompt for macOS Screen Recording permission. Grant it and relaunch.\n\n### 2. Screenpipe API token\n\nThe local API now requires bearer auth. Retrieve your token and export it:\n\n```bash\nexport SCREENPIPE_TOKEN=$(screenpipe auth token)\n```\n\n(Or set `screenpipe.token` directly in `config.yaml` — env var is preferred since it keeps secrets out of version control.)\n\n### 3. Python environment\n\nVia `pipenv` from the repo root:\n\n```bash\npipenv install httpx pyyaml sentence-transformers\n```\n\nThe embedding model (`sentence-transformers\u002Fall-MiniLM-L6-v2`, ~80 MB) downloads on first run.\n\n### 4. Local LLM (default path) — LM Studio\n\n- Install [LM Studio](https:\u002F\u002Flmstudio.ai\u002F).\n- Download `Gemma-4-31B-it` (or another strong reasoning model; adjust `local.model` in `config.yaml`).\n- Load it via the CLI for headless use (no GUI required):\n\n```bash\nlms load gemma-4-31b-it --context-length 131072 --gpu max -y\nlms status   # confirm server running on :1234\n```\n\n### 5. Cloud LLM backends (optional, opt-in)\n\nOnly if you explicitly opt out of local:\n- `claude`: set `ANTHROPIC_API_KEY`, flip `backend: claude` in `config.yaml`.\n- `foundry`: set `FOUNDRY_API_KEY`, flip `backend: foundry`, set `foundry.endpoint` to your corporate gateway URL.\n\n## Architecture\n\n```\nscreenpipe daemon (user-installed)\n        │  HTTP on localhost:3030\n        ▼\nscripts\u002Ffetch_window.py    → normalized timeline events\nscripts\u002Fredact.py          → regex scrub (defense-in-depth)\nscripts\u002Fcluster.py         → sessions + clusters (local only)\nscripts\u002Fmatch_skills.py    → top-k vs existing 135 skills (local embeddings)\nscripts\u002Fsynthesize.py      → LLM judge: reuse \u002F compose \u002F novel\n        │\n        ▼\n~\u002F.autoskill\u002Fproposed\u002F\u003Ctimestamp>\u002F        (default; override with --out)\n  ├── report.md\n  ├── composition-recipes\u002F\u003Cname>\u002FSKILL.md\n  └── new-skills\u002F\u003Cname>\u002FSKILL.md\n\nscripts\u002Fpromote.py         → user-approved proposal → skills\u002F\u003Cname>\u002F\n```\n\n## Workflow\n\nThe skill ships a unified CLI at `scripts\u002Fautoskill.py` with three subcommands:\n\n```bash\npython scripts\u002Fautoskill.py doctor   --config config.yaml --skills-dir ..\u002F\npython scripts\u002Fautoskill.py run      --start ... --end ... --config config.yaml\npython scripts\u002Fautoskill.py promote  --proposed ~\u002F.autoskill\u002Fproposed\u002F\u003Cts> --skills-dir ..\u002F --name \u003Cskill>\n```\n\n### 0. Preflight with `doctor`\n\nBefore a full run, verify every dependency in one shot:\n\n```bash\npython scripts\u002Fautoskill.py doctor \\\n  --config skills\u002Fautoskill\u002Fconfig.yaml \\\n  --skills-dir skills\n```\n\nThe report covers `config` (backend choice valid), `skills_dir` (exists), `screenpipe` (reachable + authed), and `llm` (LM Studio serving or API key present). Non-zero exit on any failure, with the offending line marked `error`.\n\n### 1. Run the pipeline\n\n```bash\nexport SCREENPIPE_TOKEN=$(screenpipe auth token)\npython scripts\u002Fautoskill.py run \\\n  --start \"2026-04-17T00:00:00Z\" \\\n  --end   \"2026-04-17T23:59:59Z\" \\\n  --config skills\u002Fautoskill\u002Fconfig.yaml \\\n  --skills-dir skills\n```\n\nProposals land in `~\u002F.autoskill\u002Fproposed\u002F\u003Ctimestamp>\u002F` by default, keeping experimental output out of the skills repo. Pass `--out PATH` to override.\n\nInternally:\n1. **Fetch** — `fetch_window` paginates screenpipe's `\u002Fsearch` endpoint, normalizes events to `{ts, app, window_title, text, content_type}`.\n2. **Redact** — `redact` scrubs emails, API keys, bearer tokens, phones from OCR text and window titles as defense-in-depth over screenpipe's own PII removal.\n3. **Cluster** — `segment_sessions` splits on idle gaps (default 10 min) and drops short sessions; `cluster_sessions` groups sessions by app-signature and keeps clusters of size `min_cluster_size` (default 2).\n4. **Match** — `load_skill_descriptions` reads frontmatter from every `SKILL.md` in `skills\u002F`; `top_k_matches` ranks each cluster against all skills using local `sentence-transformers` embeddings (cosine similarity).\n5. **Synthesize** — `synthesize` prompts the configured LLM backend to classify each cluster as `reuse`, `compose`, or `novel` and emit a SKILL.md body where appropriate.\n6. **Report** — writes `\u003Cout_dir>\u002F\u003Cts>\u002Freport.md`, plus `new-skills\u002F\u003Cname>\u002FSKILL.md` or `composition-recipes\u002F\u003Cname>\u002FSKILL.md` for each proposal.\n\nAdd `--dry-run` to stop after clustering; this skips the LLM (and the sentence-transformers load), writing only `plan.md` for inspection.\n\n### 2. Review and promote\n\nOpen `~\u002F.autoskill\u002Fproposed\u002F\u003Cts>\u002Freport.md`, edit drafts in place, delete anything you don't want. Then:\n\n```bash\npython scripts\u002Fautoskill.py promote \\\n  --proposed ~\u002F.autoskill\u002Fproposed\u002F2026-04-17T14-30-00 \\\n  --skills-dir skills \\\n  --name zotero-pubmed-helper\n```\n\n`promote` moves the directory into `skills\u002F\u003Cname>\u002F`, refusing to overwrite an existing skill. Exits non-zero with a friendly error if the proposal isn't found or the target already exists.\n\n## Configuration\n\nSee `config.yaml` for the full shape. Default values (local-first):\n\n```yaml\nbackend: local\nlocal:\n  endpoint: http:\u002F\u002Flocalhost:1234\u002Fv1   # LM Studio's Developer server\n  model: Gemma-4-31B-it\n\nscreenpipe:\n  url: http:\u002F\u002Flocalhost:3030           # or https:\u002F\u002Fscreenpipe.local via Caddy\n\ncluster:\n  min_session_minutes: 5\n  idle_gap_minutes: 10\n  min_cluster_size: 2\n```\n\nTo opt into a cloud backend:\n\n```yaml\nbackend: claude                         # or foundry\nclaude:\n  model: claude-opus-4-7\n```\n\n## Composition recipes vs new skills\n\n- **compose**: the LLM judged that chaining existing skills covers the workflow. The emitted SKILL.md is intentionally thin — frontmatter + a \"Workflow\" section that invokes existing skills in order. The same agent runtime that discovered the skill can then invoke it end-to-end.\n- **novel**: no combination of existing skills covers it. A fuller SKILL.md is drafted, still following repo conventions (frontmatter, Overview, When to Use, Workflow). The user should always review new-skill drafts before promoting.\n\n## Testing\n\nThe skill is covered by a small pytest suite at `tests\u002Fautoskill\u002F` in the repository root. Each script is unit-tested in isolation with dependency injection (mock HTTP transport, stub backend, stub embedder):\n\n```bash\npython -m pytest tests\u002Fautoskill -v\n```\n\n## Composition with other skills in this repo\n\nThe autoskill's embedding index covers all 135 sibling skills. Workflows that look like scientific writing will match `scientific-writing` \u002F `literature-review` \u002F `citation-management`; figure work will match `scientific-schematics` \u002F `generate-image` \u002F `infographics`; slide prep matches `scientific-slides` \u002F `pptx`; etc. When a cluster scores high against two or three sibling skills the emitted composition recipe names them explicitly, so the user's future agent invocations use the optimized paths already documented in this repo.\n\n## Agent operating procedure\n\n1. **Check the environment.** Confirm the objective, evaluation metric, budget (time, compute, money) and stopping criteria.\n2. **Pin down the inputs.** Confirm formats, identifiers and parameters from the data or the user. Ask rather than guess any value that changes the result.\n3. **Run a small version first.** Run one iteration end to end and inspect logs before scaling up.\n4. **Execute the full task** using the instructions and references above.\n5. **Validate the result.** Evaluate on held-out data; keep an audit trail of every iteration, hypothesis and result.\n6. **Report.** State what was run (versions, commands, parameters), what was checked, and what is still uncertain.\n\n| If this happens | Do this |\n|---|---|\n| An iteration produces suspiciously large gains | Check for leakage or evaluation bugs before accepting the result. |\n| A function, flag or endpoint in these instructions is missing in the installed version | Check the installed version's own documentation (`help()`, `--help`, official docs), adapt, and tell the user. Never invent an API. |\n| A required input, identifier or parameter is ambiguous | Ask the user, or state the assumption explicitly before running. |\n\n**Integrity rules**\n\n- Never fabricate results, parameters, identifiers, citations or statistics. If something cannot be run or verified, say so plainly.\n- Record negative results; never select or report only favourable runs.\n- Treat version-specific details here as possibly outdated: confirm them against the official documentation for the installed version.\n- Ask before actions that cost money, consume shared GPUs or cloud quota, touch personal or patient data, or cannot be undone.\n\n## Related skills\n\n- `research-skill-creator`: Create, improve and test agent skills for research workflows (paper writing, lab protocols, analysis pipelines, domain databases) that meet…\n",{"name":5,"license":15,"metadata":61,"description":7,"allowed-tools":81},{"tags":62,"version":63,"category":64,"openclaw":65,"maintainer":80},"skill authoring, workflow automation, research automation, AI agents","1.4","research-automation",{"envVars":66,"requires":77,"primaryEnv":68},[67,71,74],{"name":68,"required":69,"description":70},"SCREENPIPE_TOKEN",true,"Auth token for the local screenpipe daemon.",{"name":72,"required":57,"description":73},"ANTHROPIC_API_KEY","For Claude API calls during skill drafting.",{"name":75,"required":57,"description":76},"FOUNDRY_API_KEY","Optional Foundry access for drafting.",{"bins":78},[79],"screenpipe","Kalaris Labs","Read Write Edit Bash","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":93,"prompt":103,"zipAvailable":69},[94,97,100],{"tool":95,"command":96},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill autoskill",{"tool":98,"command":99},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill autoskill",{"tool":101,"command":102},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill autoskill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002FSKILL.md",[105,111,117,121,125,131,135,139,143,147,151,155,159,163],{"path":106,"resourceType":107,"resourceTypeDesc":108,"sizeBytes":109,"sourceHtmlUrl":110},".gitignore","OTHER","其他",34,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002F.gitignore",{"path":112,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":115,"sourceHtmlUrl":116},"config.yaml","REFERENCE","参考文档",2030,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fconfig.yaml",{"path":118,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Fhttps-proxy.md",1518,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Freferences\u002Fhttps-proxy.md",{"path":122,"resourceType":113,"resourceTypeDesc":114,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Fscreenpipe-config.yaml",1567,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Freferences\u002Fscreenpipe-config.yaml",{"path":126,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":129,"sourceHtmlUrl":130},"scripts\u002Fautoskill.py","SCRIPT","脚本",1158,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fautoskill.py",{"path":132,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":133,"sourceHtmlUrl":134},"scripts\u002Fbackends.py",3893,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fbackends.py",{"path":136,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":137,"sourceHtmlUrl":138},"scripts\u002Fcluster.py",1723,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fcluster.py",{"path":140,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":141,"sourceHtmlUrl":142},"scripts\u002Fdoctor.py",3655,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fdoctor.py",{"path":144,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":145,"sourceHtmlUrl":146},"scripts\u002Ffetch_window.py",1172,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Ffetch_window.py",{"path":148,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":149,"sourceHtmlUrl":150},"scripts\u002Fmatch_skills.py",1316,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fmatch_skills.py",{"path":152,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":153,"sourceHtmlUrl":154},"scripts\u002Fpromote.py",1559,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fpromote.py",{"path":156,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":157,"sourceHtmlUrl":158},"scripts\u002Fredact.py",1634,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fredact.py",{"path":160,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":161,"sourceHtmlUrl":162},"scripts\u002Frun.py",7666,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Frun.py",{"path":164,"resourceType":127,"resourceTypeDesc":128,"sizeBytes":165,"sourceHtmlUrl":166},"scripts\u002Fsynthesize.py",2378,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FKalarisLabs\u002Fresearch-agent-skills\u002Fskills\u002Fautoskill\u002Fscripts\u002Fsynthesize.py",[168,177,185,193,201,209],{"skillNo":169,"name":170,"nameZh":6,"description":171,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":172,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":176},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":181,"sourceHtmlUrl":182,"categories":183,"keywords":184,"publishedAt":176},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":189,"sourceHtmlUrl":190,"categories":191,"keywords":192,"publishedAt":176},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":194,"name":195,"nameZh":6,"description":196,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":197,"sourceHtmlUrl":198,"categories":199,"keywords":200,"publishedAt":176},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":205,"sourceHtmlUrl":206,"categories":207,"keywords":208,"publishedAt":176},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":213,"sourceHtmlUrl":214,"categories":215,"keywords":216,"publishedAt":176},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]