[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APWFSA6NYJB0RER2015EVR":3,"skill-same:01M7APWFSA6NYJB0RER2015EVR":47},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7APWFSA6NYJB0RER2015EVR","intent-driven-development",null,"Turn ambiguous or high-impact product and engineering changes into scoped, verifiable acceptance criteria before or alongside implementation. Use when a user asks to clarify a feature, define acceptance criteria, de-risk a security\u002Fdata\u002Fmigration\u002Fintegration change, prepare implementation requirements for another agent, or make a complex request testable. Do not trigger for trivial edits, straightforward fixes, active debugging, code review, or implementation requests whose acceptance conditions are already clear unless the user explicitly invokes this skill.","Cyrilthetecchieee\u002Fcyril-code-","Cyrilthetecchieee","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219787998?v=4","01M7AF0MMMKRAA0H61XMJPV92H","Julian Cyril D ","01M7AF0MQ10AVG6QJQ1C2BC0F5",2,"MIT","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fskills\u002Fintent-driven-development\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: intent-driven-development\ndescription: Turn ambiguous or high-impact product and engineering changes into scoped, verifiable acceptance criteria before or alongside implementation. Use when a user asks to clarify a feature, define acceptance criteria, de-risk a security\u002Fdata\u002Fmigration\u002Fintegration change, prepare implementation requirements for another agent, or make a complex request testable. Do not trigger for trivial edits, straightforward fixes, active debugging, code review, or implementation requests whose acceptance conditions are already clear unless the user explicitly invokes this skill.\n---\n\n# Intent-Driven Development\n\nProduce useful acceptance criteria without turning specification into ceremony. Inspect\navailable context first, expose genuine ambiguity, and choose verification methods that fit\nthe work and its risk.\n\n## When to Activate\n\n- User asks to clarify a feature, define acceptance criteria, or de-risk a change before implementation\n- Request touches security, authentication, persistent data, migrations, external APIs, or compliance\n- User wants to prepare a handoff artifact for another agent or team\n- Request is ambiguous enough that the expected outcome is not yet observable or testable\n- User explicitly invokes this skill with `\u002Fintent-driven-development`\n\nDo not activate for trivial edits, straightforward one-line fixes, active debugging sessions,\ncode review requests, or implementation requests whose acceptance conditions are already clear.\n\n## How It Works\n\n1. **Inspect context first** — reads the repository, docs, schemas, and test infrastructure for technical facts before asking any question, while treating product\u002Fbusiness constraints as something only the user or a product artifact can supply\n2. **Choose depth** — selects Quick Capture (3-7 criteria, low\u002Fmoderate risk) or Full Acceptance Brief (security, data, migration, cross-system changes) based on the risk profile\n3. **Ask minimally** — only asks questions whose answers cannot be inferred and that materially change scope or behavior\n4. **Write observable criteria** — each AC-NNN describes a starting condition, trigger, expected outcome, prohibited side effect, verification method, and priority; no vague words like \"correctly\" or \"securely\" without evidence\n5. **Proceed or hand off** — for clear requests with no blocking risks, records criteria and continues; for risky changes, presents blockers and waits for confirmation\n6. **Handle revision** — if an AC fails mid-implementation due to architectural constraints, marks it `[revised]`, updates scope or verification method, increments the revision number, and re-presents only the changed criteria\n\n## Examples\n\n**Quick Capture — \"Add CSV export to the dashboard\"**\n\n```\nGoal: Authenticated users can download dashboard data as a CSV file.\nIn scope: Export of currently filtered rows; filename includes date.\nOut of scope: Scheduled exports, email delivery, Excel format.\nAssumptions: Max row count is under 10k; no PII in exported fields.\n\nAC-001: Export generates file with correct headers\n- Scenario: authenticated user, at least one data row visible\n- Action: click \"Export CSV\"\n- Expected: browser downloads file with columns [id, name, created_at]\n- Must not: expose internal fields or rows belonging to other users\n- Verification: automated integration test + manual schema spot-check\n- Priority: Required\n```\n\n**Full Acceptance Brief trigger — \"Migrate user auth to OAuth\"**\n\nAuth change + external dependency + existing session data → Full Brief with Risk Review table,\nblocking decisions on session invalidation strategy, and explicit rollback AC.\n\n**Existing spec review — user pastes a PRD**\n\nSkill reviews it for missing scope boundaries, unverifiable requirements (\"the system shall be fast\"),\nand silent assumptions, then returns corrected or supplemental criteria without restarting discovery.\n\n## Operating Rules\n\n1. Inspect the available repository, documentation, issue, design, and test context before\n   asking for technical facts that can be discovered locally.\n2. Do not infer product or business constraints from code. Business rules, compliance and\n   regulatory obligations, contractual SLAs, pricing, data-retention policy, prioritization,\n   and target users cannot be read from a repository. Treat them as unknown until the user\n   supplies them or an authoritative product artifact (PRD, contract, policy document) states\n   them. Record them as assumptions flagged for confirmation, never as discovered facts. The\n   repository tells you how the system behaves today, not what the business requires it to do.\n3. Ask only questions whose answers are required and cannot be safely inferred. Group short,\n   related questions when that saves unnecessary turns.\n4. Do not block implementation by default. When the user has asked to implement a sufficiently\n   clear change, record key assumptions and acceptance criteria briefly, then proceed or hand\n   them to the implementation workflow.\n5. Require explicit user confirmation before proceeding only when an unresolved decision could\n   create material security exposure, data loss, irreversible migration, contractual\u002FAPI\n   breakage, meaningful cost, or destructive external action.\n6. Do not write an acceptance document into a repository, alter project files, create a branch,\n   commit, or invoke another skill unless the user requests it or the active repository\n   workflow explicitly requires it.\n7. Treat automated tests as evidence, not truth. Prefer automation when reliable and\n   proportionate; allow manual UX, accessibility, security, legal, or operational verification\n   where automation cannot establish the outcome.\n8. Never include real secrets, credentials, tokens, private keys, personal data, or sensitive\n   production payloads in acceptance criteria, fixtures, examples, or saved artifacts. Use\n   redacted or synthetic values.\n9. Do not run destructive tests, migrations, security probes, load tests, paid external calls,\n   or operations against production\u002Flive data without explicit authorization and an identified\n   safe environment.\n10. When an acceptance criterion cannot be satisfied due to an architectural, platform, or\n   external constraint discovered during implementation, do not silently drop or workaround it.\n   Update the affected criterion (mark it `[revised]`, state the constraint, and adjust scope or\n   verification method), increment the revision number, and re-present only the changed criteria\n   to the user before continuing. Require explicit confirmation only if the revision changes a\n   blocking decision or materially reduces safety or correctness guarantees.\n\n## Choose The Depth\n\nUse the smallest useful output.\n\n### Quick Capture\n\nUse for a clear but non-trivial change with low or moderate risk. Produce:\n\n- Goal\n- In scope \u002F out of scope\n- Assumptions\n- 3-7 acceptance criteria with verification methods\n- Blocking questions, if any\n\nDo not delay implementation for approval unless a blocking risk from the operating rules\nexists or the user specifically asked for a specification first.\n\n### Full Acceptance Brief\n\nUse for ambiguous, cross-system, security-sensitive, data-changing, migration, compliance,\nor high-cost changes, or when the user requests a handoff artifact. Produce the full template\nbelow and request confirmation for unresolved blocking decisions before risky implementation.\n\n### Existing Specification Review\n\nWhen the user already supplied a PRD, issue, plan, or acceptance criteria:\n\n1. Review it instead of restarting discovery.\n2. Identify missing scope boundaries, unsafe assumptions, contradictions, and unverifiable\n   requirements.\n3. Return corrected or supplemental criteria.\n\n## Workflow\n\n### 1. Establish Goal And Risk\n\nExtract or ask for:\n\n- The observable outcome for the user or system.\n- The actors affected.\n- The main failure consequence.\n- Risk dimensions that actually apply: security\u002Fprivacy, persistent data, compatibility\u002FAPI,\n  migration, external dependencies, cost, concurrency, performance, usability\u002Faccessibility.\n\nAvoid asking generic questions about irrelevant risks.\n\n### 2. Discover Context\n\nWhen local or connected artifacts are available, inspect only what is needed:\n\n- Existing behavior and directly related files or interfaces.\n- Repository conventions, product docs, API contracts, data schemas, or migration history.\n- Existing verification infrastructure and realistic commands.\n- External dependencies and whether they are testable in isolation.\n\nRecord discovered facts separately from user-provided assumptions. If context cannot be\ninspected, say what is unknown and ask focused questions.\n\nThe repository reveals technical facts — how the system behaves today, its conventions, and\nits contracts. It does not reveal product or business constraints: business rules, compliance\nand regulatory obligations, contractual SLAs, pricing, data-retention policy, prioritization,\nand target users. Never reconstruct these from code or naming. Capture them only from the user\nor an authoritative product artifact, and list them as assumptions to confirm until then.\n\n### 3. Define Scope\n\nState:\n\n- Goal: one sentence describing the intended outcome.\n- In scope: behavior this change must deliver.\n- Out of scope: tempting adjacent work explicitly excluded.\n- Assumptions: claims not yet proven.\n- Blocking decisions: unresolved choices that materially affect safety or behavior.\n\n### 4. Write Acceptance Criteria\n\nUse `AC-001`, `AC-002`, and so on. Each criterion must describe observable behavior and an\nappropriate verification method; criteria and tests are not required to map one-to-one.\n\nFor each applicable criterion include:\n\n- Scenario or starting condition.\n- Action or trigger.\n- Expected observable behavior.\n- Prohibited side effect when meaningful.\n- Verification method: automated test, integration check, manual UX review, accessibility\n  check, security review, operational check, or stakeholder acceptance.\n- Environment\u002Fsafety constraint when verification could affect data, services, cost, or secrets.\n- Priority: required, important, or optional.\n\nDo not use words such as \"correctly\", \"securely\", \"fast\", \"intuitive\", or \"robust\" without\ndefining observable evidence or recording them as a human-review judgment.\n\n### 5. Cover Only Relevant Boundaries\n\nConsider these categories, but include only categories that apply:\n\n| Category | Include when | Typical evidence |\n| --- | --- | --- |\n| Happy path | New or changed user-visible behavior | Successful workflow or state transition |\n| Validation | The change accepts input | Rejected malformed or boundary value without mutation |\n| Authorization\u002Fprivacy | Data or actions have access boundaries | Denied access and no sensitive disclosure |\n| Persistence\u002Fmigration | Stored data or schemas change | Backward read, migration, rollback or backup behavior |\n| Compatibility | Public APIs, files, events, or clients may break | Existing contract or fixture remains valid |\n| Failure recovery | Network, service, or asynchronous failure exists | No partial state or clear retry\u002Fdegraded behavior |\n| Idempotency\u002Fconcurrency | Repeats or simultaneous writes are plausible | No duplicate side effect or invalid final state |\n| Performance | A user or service threshold matters | Defined measurement conditions and threshold |\n| UX\u002Faccessibility | A person interacts with the result | Keyboard, feedback, error recovery, visual\u002Fmanual review |\n\n### 6. Present And Continue\n\n- For a clarification\u002Fspecification request, present the brief and ask for decisions only on\n  listed blockers.\n- For an implementation request with no blocker, present a compact criteria summary as part of\n  the work and continue with implementation.\n- For handoff to another agent or team, include enough context and verification detail for them\n  to act without inventing requirements.\n- Save the brief to a file only when requested. Use a repository-approved path when one exists;\n  otherwise ask for or state the chosen destination before writing.\n\n## Output Template\n\nUse this template for a Full Acceptance Brief. Omit irrelevant sections for Quick Capture.\n\n```markdown\n# Acceptance Brief: \u003CChange Name>\n\n**Status:** Draft | Approved | Implemented | Verified\n**Revision:** \u003Cnumber>\n**Prepared for:** \u003Cuser\u002Fteam\u002Fagent, when known>\n**Approval required before risky work:** Yes | No - \u003Creason>\n\n## Revision Log\n\n| Rev | Date | Changed criteria | Reason |\n| --- | --- | --- | --- |\n| 1 | \u003Cdate> | — | Initial draft |\n\n## Goal\n\n\u003COne observable outcome sentence.>\n\n## Scope\n\n**In scope**\n- \u003Cbehavior included>\n\n**Out of scope**\n- \u003Cadjacent work excluded>\n\n## Context\n\n**Discovered facts** (technical, verified from repository or artifact)\n- \u003Chow the system behaves today, conventions, contracts>\n\n**Product\u002Fbusiness constraints** (supplied by user or product artifact, never inferred from code)\n- \u003Cbusiness rule, compliance\u002FSLA obligation, retention policy, priority, target user — or \"none supplied yet\">\n\n**Assumptions**\n- \u003Cunverified claim to confirm or validate>\n\n**Dependencies and constraints**\n- \u003Cexternal service, local convention, compatibility obligation, environment limit>\n\n## Risk Review\n\n| Risk area | Applies? | Required handling |\n| --- | --- | --- |\n| Security\u002Fprivacy | Yes\u002FNo | \u003Credaction, authorization, review, etc.> |\n| Persistent data\u002Fmigration | Yes\u002FNo | \u003Ccompatibility, backup, rollback, etc.> |\n| External effects\u002Fcost | Yes\u002FNo | \u003Csandbox\u002Ftest environment\u002Fauthorization> |\n| Compatibility\u002FAPI | Yes\u002FNo | \u003Ccontract to preserve or version> |\n| UX\u002Faccessibility | Yes\u002FNo | \u003Cmanual or automated evidence> |\n\n## Acceptance Criteria\n\n### AC-001: \u003Cobservable behavior>\n- **Scenario:** \u003Cstarting condition>\n- **Action:** \u003Csingle trigger>\n- **Expected:** \u003Cobservable result>\n- **Must not:** \u003Cprohibited side effect, if applicable>\n- **Verification:** \u003Cmethod and intended evidence>\n- **Environment\u002Fsafety:** \u003Cconstraints, if applicable>\n- **Priority:** Required | Important | Optional\n\n## Blocking Decisions\n\n- [ ] \u003Conly decisions that prevent safe or correct progress>\n\n## Verification Plan\n\n| Criterion | Verification evidence | Status |\n| --- | --- | --- |\n| AC-001 | \u003Ctest\u002Fcheck\u002Freview command or evidence type> | Pending |\n```\n\n## Pass\u002FFail Examples\n\nUse these to judge whether the skill actually produced a verifiable brief, not planning prose.\n\n**A failing acceptance criterion**\n\n```\nAC-001: The export works correctly and is secure.\n```\n\nFails — \"works correctly\" and \"secure\" are not observable, there is no scenario, trigger,\nexpected result, or verification method, and nothing states what must not happen. A reader\ncannot tell whether the implementation satisfied it.\n\n**A passing acceptance criterion**\n\n```\nAC-001: Export generates file with correct headers\n- Scenario: authenticated user, at least one data row visible\n- Action: click \"Export CSV\"\n- Expected: browser downloads file with columns [id, name, created_at]\n- Must not: expose internal fields or rows belonging to other users\n- Verification: automated integration test + manual schema spot-check\n- Priority: Required\n```\n\nPasses — a concrete observable outcome, a prohibited side effect, and a named verification\nmethod. Two people would agree on whether it was met.\n\n**A failing context entry**\n\n```\nDiscovered facts: Users on the free tier are limited to 100 exports per month.\n```\n\nFails — a per-tier limit is a business rule. It must not appear under discovered facts inferred\nfrom code; it belongs under Product\u002Fbusiness constraints, supplied by the user, or be listed as\nan assumption to confirm.\n\n### Pass\u002FFail Rubric\n\nA brief passes only if every answer is \"yes\". Any \"no\" means revise before returning it.\n\n- [ ] Does every required criterion have a scenario, an observable expected result, and a named verification method?\n- [ ] Are all vague terms (\"correctly\", \"secure\", \"fast\", \"robust\") either replaced with observable evidence or marked as human judgment?\n- [ ] Are product\u002Fbusiness constraints listed as supplied\u002Fassumed, with none silently inferred from code?\n- [ ] Is scope explicit, with out-of-scope items named?\n- [ ] Are blocking decisions limited to choices that actually affect safety or correctness, not preferences?\n\n## Quality Check\n\nBefore returning the brief, check:\n\n- The goal describes an outcome rather than an implementation choice.\n- Scope boundaries and assumptions are explicit.\n- Every required criterion is observable or clearly marked for human judgment.\n- Security, privacy, data, compatibility, external-effect, and UX risks were considered only\n  where relevant and not silently ignored.\n- Verification methods identify safe environments for risky operations.\n- No secret or production-sensitive information was copied into the output.\n- No repository mutation or implementation block is imposed without justification or request.\n\n## Handoff\n\nWhen another planning or implementation workflow is available, pass the acceptance brief or\ncriterion IDs to it. When no dedicated workflow exists, provide the brief directly as the\nimplementation reference. Do not assume any named skill or tool is installed.\n","# Intent-Driven Development\n\nProduce useful acceptance criteria without turning specification into ceremony. Inspect\navailable context first, expose genuine ambiguity, and choose verification methods that fit\nthe work and its risk.\n\n## When to Activate\n\n- User asks to clarify a feature, define acceptance criteria, or de-risk a change before implementation\n- Request touches security, authentication, persistent data, migrations, external APIs, or compliance\n- User wants to prepare a handoff artifact for another agent or team\n- Request is ambiguous enough that the expected outcome is not yet observable or testable\n- User explicitly invokes this skill with `\u002Fintent-driven-development`\n\nDo not activate for trivial edits, straightforward one-line fixes, active debugging sessions,\ncode review requests, or implementation requests whose acceptance conditions are already clear.\n\n## How It Works\n\n1. **Inspect context first** — reads the repository, docs, schemas, and test infrastructure for technical facts before asking any question, while treating product\u002Fbusiness constraints as something only the user or a product artifact can supply\n2. **Choose depth** — selects Quick Capture (3-7 criteria, low\u002Fmoderate risk) or Full Acceptance Brief (security, data, migration, cross-system changes) based on the risk profile\n3. **Ask minimally** — only asks questions whose answers cannot be inferred and that materially change scope or behavior\n4. **Write observable criteria** — each AC-NNN describes a starting condition, trigger, expected outcome, prohibited side effect, verification method, and priority; no vague words like \"correctly\" or \"securely\" without evidence\n5. **Proceed or hand off** — for clear requests with no blocking risks, records criteria and continues; for risky changes, presents blockers and waits for confirmation\n6. **Handle revision** — if an AC fails mid-implementation due to architectural constraints, marks it `[revised]`, updates scope or verification method, increments the revision number, and re-presents only the changed criteria\n\n## Examples\n\n**Quick Capture — \"Add CSV export to the dashboard\"**\n\n```\nGoal: Authenticated users can download dashboard data as a CSV file.\nIn scope: Export of currently filtered rows; filename includes date.\nOut of scope: Scheduled exports, email delivery, Excel format.\nAssumptions: Max row count is under 10k; no PII in exported fields.\n\nAC-001: Export generates file with correct headers\n- Scenario: authenticated user, at least one data row visible\n- Action: click \"Export CSV\"\n- Expected: browser downloads file with columns [id, name, created_at]\n- Must not: expose internal fields or rows belonging to other users\n- Verification: automated integration test + manual schema spot-check\n- Priority: Required\n```\n\n**Full Acceptance Brief trigger — \"Migrate user auth to OAuth\"**\n\nAuth change + external dependency + existing session data → Full Brief with Risk Review table,\nblocking decisions on session invalidation strategy, and explicit rollback AC.\n\n**Existing spec review — user pastes a PRD**\n\nSkill reviews it for missing scope boundaries, unverifiable requirements (\"the system shall be fast\"),\nand silent assumptions, then returns corrected or supplemental criteria without restarting discovery.\n\n## Operating Rules\n\n1. Inspect the available repository, documentation, issue, design, and test context before\n   asking for technical facts that can be discovered locally.\n2. Do not infer product or business constraints from code. Business rules, compliance and\n   regulatory obligations, contractual SLAs, pricing, data-retention policy, prioritization,\n   and target users cannot be read from a repository. Treat them as unknown until the user\n   supplies them or an authoritative product artifact (PRD, contract, policy document) states\n   them. Record them as assumptions flagged for confirmation, never as discovered facts. The\n   repository tells you how the system behaves today, not what the business requires it to do.\n3. Ask only questions whose answers are required and cannot be safely inferred. Group short,\n   related questions when that saves unnecessary turns.\n4. Do not block implementation by default. When the user has asked to implement a sufficiently\n   clear change, record key assumptions and acceptance criteria briefly, then proceed or hand\n   them to the implementation workflow.\n5. Require explicit user confirmation before proceeding only when an unresolved decision could\n   create material security exposure, data loss, irreversible migration, contractual\u002FAPI\n   breakage, meaningful cost, or destructive external action.\n6. Do not write an acceptance document into a repository, alter project files, create a branch,\n   commit, or invoke another skill unless the user requests it or the active repository\n   workflow explicitly requires it.\n7. Treat automated tests as evidence, not truth. Prefer automation when reliable and\n   proportionate; allow manual UX, accessibility, security, legal, or operational verification\n   where automation cannot establish the outcome.\n8. Never include real secrets, credentials, tokens, private keys, personal data, or sensitive\n   production payloads in acceptance criteria, fixtures, examples, or saved artifacts. Use\n   redacted or synthetic values.\n9. Do not run destructive tests, migrations, security probes, load tests, paid external calls,\n   or operations against production\u002Flive data without explicit authorization and an identified\n   safe environment.\n10. When an acceptance criterion cannot be satisfied due to an architectural, platform, or\n   external constraint discovered during implementation, do not silently drop or workaround it.\n   Update the affected criterion (mark it `[revised]`, state the constraint, and adjust scope or\n   verification method), increment the revision number, and re-present only the changed criteria\n   to the user before continuing. Require explicit confirmation only if the revision changes a\n   blocking decision or materially reduces safety or correctness guarantees.\n\n## Choose The Depth\n\nUse the smallest useful output.\n\n### Quick Capture\n\nUse for a clear but non-trivial change with low or moderate risk. Produce:\n\n- Goal\n- In scope \u002F out of scope\n- Assumptions\n- 3-7 acceptance criteria with verification methods\n- Blocking questions, if any\n\nDo not delay implementation for approval unless a blocking risk from the operating rules\nexists or the user specifically asked for a specification first.\n\n### Full Acceptance Brief\n\nUse for ambiguous, cross-system, security-sensitive, data-changing, migration, compliance,\nor high-cost changes, or when the user requests a handoff artifact. Produce the full template\nbelow and request confirmation for unresolved blocking decisions before risky implementation.\n\n### Existing Specification Review\n\nWhen the user already supplied a PRD, issue, plan, or acceptance criteria:\n\n1. Review it instead of restarting discovery.\n2. Identify missing scope boundaries, unsafe assumptions, contradictions, and unverifiable\n   requirements.\n3. Return corrected or supplemental criteria.\n\n## Workflow\n\n### 1. Establish Goal And Risk\n\nExtract or ask for:\n\n- The observable outcome for the user or system.\n- The actors affected.\n- The main failure consequence.\n- Risk dimensions that actually apply: security\u002Fprivacy, persistent data, compatibility\u002FAPI,\n  migration, external dependencies, cost, concurrency, performance, usability\u002Faccessibility.\n\nAvoid asking generic questions about irrelevant risks.\n\n### 2. Discover Context\n\nWhen local or connected artifacts are available, inspect only what is needed:\n\n- Existing behavior and directly related files or interfaces.\n- Repository conventions, product docs, API contracts, data schemas, or migration history.\n- Existing verification infrastructure and realistic commands.\n- External dependencies and whether they are testable in isolation.\n\nRecord discovered facts separately from user-provided assumptions. If context cannot be\ninspected, say what is unknown and ask focused questions.\n\nThe repository reveals technical facts — how the system behaves today, its conventions, and\nits contracts. It does not reveal product or business constraints: business rules, compliance\nand regulatory obligations, contractual SLAs, pricing, data-retention policy, prioritization,\nand target users. Never reconstruct these from code or naming. Capture them only from the user\nor an authoritative product artifact, and list them as assumptions to confirm until then.\n\n### 3. Define Scope\n\nState:\n\n- Goal: one sentence describing the intended outcome.\n- In scope: behavior this change must deliver.\n- Out of scope: tempting adjacent work explicitly excluded.\n- Assumptions: claims not yet proven.\n- Blocking decisions: unresolved choices that materially affect safety or behavior.\n\n### 4. Write Acceptance Criteria\n\nUse `AC-001`, `AC-002`, and so on. Each criterion must describe observable behavior and an\nappropriate verification method; criteria and tests are not required to map one-to-one.\n\nFor each applicable criterion include:\n\n- Scenario or starting condition.\n- Action or trigger.\n- Expected observable behavior.\n- Prohibited side effect when meaningful.\n- Verification method: automated test, integration check, manual UX review, accessibility\n  check, security review, operational check, or stakeholder acceptance.\n- Environment\u002Fsafety constraint when verification could affect data, services, cost, or secrets.\n- Priority: required, important, or optional.\n\nDo not use words such as \"correctly\", \"securely\", \"fast\", \"intuitive\", or \"robust\" without\ndefining observable evidence or recording them as a human-review judgment.\n\n### 5. Cover Only Relevant Boundaries\n\nConsider these categories, but include only categories that apply:\n\n| Category | Include when | Typical evidence |\n| --- | --- | --- |\n| Happy path | New or changed user-visible behavior | Successful workflow or state transition |\n| Validation | The change accepts input | Rejected malformed or boundary value without mutation |\n| Authorization\u002Fprivacy | Data or actions have access boundaries | Denied access and no sensitive disclosure |\n| Persistence\u002Fmigration | Stored data or schemas change | Backward read, migration, rollback or backup behavior |\n| Compatibility | Public APIs, files, events, or clients may break | Existing contract or fixture remains valid |\n| Failure recovery | Network, service, or asynchronous failure exists | No partial state or clear retry\u002Fdegraded behavior |\n| Idempotency\u002Fconcurrency | Repeats or simultaneous writes are plausible | No duplicate side effect or invalid final state |\n| Performance | A user or service threshold matters | Defined measurement conditions and threshold |\n| UX\u002Faccessibility | A person interacts with the result | Keyboard, feedback, error recovery, visual\u002Fmanual review |\n\n### 6. Present And Continue\n\n- For a clarification\u002Fspecification request, present the brief and ask for decisions only on\n  listed blockers.\n- For an implementation request with no blocker, present a compact criteria summary as part of\n  the work and continue with implementation.\n- For handoff to another agent or team, include enough context and verification detail for them\n  to act without inventing requirements.\n- Save the brief to a file only when requested. Use a repository-approved path when one exists;\n  otherwise ask for or state the chosen destination before writing.\n\n## Output Template\n\nUse this template for a Full Acceptance Brief. Omit irrelevant sections for Quick Capture.\n\n```markdown\n# Acceptance Brief: \u003CChange Name>\n\n**Status:** Draft | Approved | Implemented | Verified\n**Revision:** \u003Cnumber>\n**Prepared for:** \u003Cuser\u002Fteam\u002Fagent, when known>\n**Approval required before risky work:** Yes | No - \u003Creason>\n\n## Revision Log\n\n| Rev | Date | Changed criteria | Reason |\n| --- | --- | --- | --- |\n| 1 | \u003Cdate> | — | Initial draft |\n\n## Goal\n\n\u003COne observable outcome sentence.>\n\n## Scope\n\n**In scope**\n- \u003Cbehavior included>\n\n**Out of scope**\n- \u003Cadjacent work excluded>\n\n## Context\n\n**Discovered facts** (technical, verified from repository or artifact)\n- \u003Chow the system behaves today, conventions, contracts>\n\n**Product\u002Fbusiness constraints** (supplied by user or product artifact, never inferred from code)\n- \u003Cbusiness rule, compliance\u002FSLA obligation, retention policy, priority, target user — or \"none supplied yet\">\n\n**Assumptions**\n- \u003Cunverified claim to confirm or validate>\n\n**Dependencies and constraints**\n- \u003Cexternal service, local convention, compatibility obligation, environment limit>\n\n## Risk Review\n\n| Risk area | Applies? | Required handling |\n| --- | --- | --- |\n| Security\u002Fprivacy | Yes\u002FNo | \u003Credaction, authorization, review, etc.> |\n| Persistent data\u002Fmigration | Yes\u002FNo | \u003Ccompatibility, backup, rollback, etc.> |\n| External effects\u002Fcost | Yes\u002FNo | \u003Csandbox\u002Ftest environment\u002Fauthorization> |\n| Compatibility\u002FAPI | Yes\u002FNo | \u003Ccontract to preserve or version> |\n| UX\u002Faccessibility | Yes\u002FNo | \u003Cmanual or automated evidence> |\n\n## Acceptance Criteria\n\n### AC-001: \u003Cobservable behavior>\n- **Scenario:** \u003Cstarting condition>\n- **Action:** \u003Csingle trigger>\n- **Expected:** \u003Cobservable result>\n- **Must not:** \u003Cprohibited side effect, if applicable>\n- **Verification:** \u003Cmethod and intended evidence>\n- **Environment\u002Fsafety:** \u003Cconstraints, if applicable>\n- **Priority:** Required | Important | Optional\n\n## Blocking Decisions\n\n- [ ] \u003Conly decisions that prevent safe or correct progress>\n\n## Verification Plan\n\n| Criterion | Verification evidence | Status |\n| --- | --- | --- |\n| AC-001 | \u003Ctest\u002Fcheck\u002Freview command or evidence type> | Pending |\n```\n\n## Pass\u002FFail Examples\n\nUse these to judge whether the skill actually produced a verifiable brief, not planning prose.\n\n**A failing acceptance criterion**\n\n```\nAC-001: The export works correctly and is secure.\n```\n\nFails — \"works correctly\" and \"secure\" are not observable, there is no scenario, trigger,\nexpected result, or verification method, and nothing states what must not happen. A reader\ncannot tell whether the implementation satisfied it.\n\n**A passing acceptance criterion**\n\n```\nAC-001: Export generates file with correct headers\n- Scenario: authenticated user, at least one data row visible\n- Action: click \"Export CSV\"\n- Expected: browser downloads file with columns [id, name, created_at]\n- Must not: expose internal fields or rows belonging to other users\n- Verification: automated integration test + manual schema spot-check\n- Priority: Required\n```\n\nPasses — a concrete observable outcome, a prohibited side effect, and a named verification\nmethod. Two people would agree on whether it was met.\n\n**A failing context entry**\n\n```\nDiscovered facts: Users on the free tier are limited to 100 exports per month.\n```\n\nFails — a per-tier limit is a business rule. It must not appear under discovered facts inferred\nfrom code; it belongs under Product\u002Fbusiness constraints, supplied by the user, or be listed as\nan assumption to confirm.\n\n### Pass\u002FFail Rubric\n\nA brief passes only if every answer is \"yes\". Any \"no\" means revise before returning it.\n\n- [ ] Does every required criterion have a scenario, an observable expected result, and a named verification method?\n- [ ] Are all vague terms (\"correctly\", \"secure\", \"fast\", \"robust\") either replaced with observable evidence or marked as human judgment?\n- [ ] Are product\u002Fbusiness constraints listed as supplied\u002Fassumed, with none silently inferred from code?\n- [ ] Is scope explicit, with out-of-scope items named?\n- [ ] Are blocking decisions limited to choices that actually affect safety or correctness, not preferences?\n\n## Quality Check\n\nBefore returning the brief, check:\n\n- The goal describes an outcome rather than an implementation choice.\n- Scope boundaries and assumptions are explicit.\n- Every required criterion is observable or clearly marked for human judgment.\n- Security, privacy, data, compatibility, external-effect, and UX risks were considered only\n  where relevant and not silently ignored.\n- Verification methods identify safe environments for risky operations.\n- No secret or production-sensitive information was copied into the output.\n- No repository mutation or implementation block is imposed without justification or request.\n\n## Handoff\n\nWhen another planning or implementation workflow is available, pass the acceptance brief or\ncriterion IDs to it. When no dedicated workflow exists, provide the brief directly as the\nimplementation reference. Do not assume any named skill or tool is installed.\n",{"name":5,"description":7},"main","57e7aa6b6e03bce1a7d7862ba9c2ec312f7f19b5","src\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fskills\u002Fintent-driven-development",0,"https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee","https:\u002F\u002Fwithcyril.me\u002F","Hi, I’m Julian Cyril D, a Computer Science and Business Systems student at PSNACET.\r\nI’m passionate about full-stack development, UI\u002FUX design, and building sma","2026-11-04 23:28:50",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Cyrilthetecchieee\u002Fcyril-code- --skill intent-driven-development",{"tool":39,"command":40},"bunx","bunx skills add Cyrilthetecchieee\u002Fcyril-code- --skill intent-driven-development",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Cyrilthetecchieee\u002Fcyril-code- --skill intent-driven-development","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fskills\u002Fintent-driven-development\u002FSKILL.md",true,[],[48,57,64,72,79,86],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":52,"licenseFileUrl":53,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7AQV6CYX8RMC78420V9WZ62","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7AQV2895N3S1MEX6K76G6G2","youtube-downloader","Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fvideo-downloader\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":52,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7AQTRNX62DNKVZ5GXEHRBKB","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftheme-factory\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AQTNNVHAAN9H6DA8T6ZVE0","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftemplate-skill\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AQTJ3MQ6AKX152MEX2MYCC","tailored-resume-generator","Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Ftailored-resume-generator\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":52,"licenseFileUrl":90,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7AQTD7D5MYET2YWG7HG9WM3","slack-gif-creator","Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like \"make me a GIF for Slack of X doing Y\".","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FCyrilthetecchieee\u002Fcyril-code-\u002Fblob\u002Fmain\u002Fsrc\u002Fcyril_code\u002Fassets\u002F.skills_repo\u002Fslack-gif-creator\u002FSKILL.md",[],[]]