AGENT SKILL

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

License 许可
MIT
最近更新
2026-11-09
Stars
★ 11
Forks
0

01 前言 Front Matter

name
verification-before-completion
description
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

02 资源文件 1

03 SKILL.md 正文

Verification Before Completion

Overview

Core principle: Evidence before claims, always.

Violating the letter of this rule is violating the spirit of this rule.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If you haven't run the verification command in this message, you cannot claim it passes.

The Gate Function

BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
   - If NO: State actual status with evidence
   - If YES: State claim WITH evidence
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying

Common Failures

Claim Requires Not Sufficient
Tests pass Test command output: 0 failures Previous run, "should pass"
Linter clean Linter output: 0 errors Partial check, extrapolation
Build succeeds Build command: exit 0 Linter passing, logs look good
Bug fixed Test original symptom: passes Code changed, assumed fixed
Regression test works Red-green cycle verified Test passes once
Agent completed VCS diff shows changes Agent reports "success"
Requirements met Line-by-line checklist Tests passing

Red Flags - STOP

  • Using "should", "probably", "seems to"
  • Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
  • About to commit/push/PR without verification
  • Trusting agent success reports
  • Relying on partial verification
  • Thinking "just this once"
  • Tired and wanting work over
  • ANY wording implying success without having run verification

Rationalization Prevention

Excuse Reality
"Should work now" RUN the verification
"I'm confident" Confidence ≠ evidence
"Just this once" No exceptions
"Linter passed" Linter ≠ compiler
"Agent said success" Verify independently
"I'm tired" Exhaustion ≠ excuse
"Partial check is enough" Partial proves nothing
"Different words so rule doesn't apply" Spirit over letter

Key Patterns

Tests:

✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"

Regression tests (TDD Red-Green):

✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)

Build:

✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)

Requirements:

✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"

Agent delegation:

✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report

When To Apply

ALWAYS before:

  • ANY variation of success/completion claims
  • ANY expression of satisfaction
  • ANY positive statement about work state
  • Committing, PR creation, task completion
  • Moving to next task
  • Delegating to agents

Rule applies to:

  • Exact phrases
  • Paraphrases and synonyms
  • Implications of success
  • ANY communication suggesting completion/correctness

04 同仓库更多 Skills

Praneeth-Suresh
Praneeth-Suresh/Beryl

using-beryl

暂无简介

★ 11
Praneeth-Suresh
Praneeth-Suresh/Beryl

understand-codebase

Teach a developer how a repository, subsystem, execution path, migration, diff, commit, branch, or pull request works. Use when the user asks to understand, explain, map, walk through, explore, or quiz themselves on code, or asks for an interactive HTML understanding artifact.

开发工程师教师与教育
★ 11
Praneeth-Suresh
Praneeth-Suresh/Beryl

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

测试与质量写作与文案
★ 11
Praneeth-Suresh
Praneeth-Suresh/Beryl

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

测试与质量
★ 11
Praneeth-Suresh
Praneeth-Suresh/Beryl

simplifying-code

Use when code in a specific module or area is hard to understand or change, when the user asks to simplify, refactor, clean up, or improve the design or architecture of some code, or when a maintenance program hands over a refactor slice. Finds unmanaged complexity from evidence and removes it with small, behavior-preserving changes.

开发工程师
★ 11
Praneeth-Suresh
Praneeth-Suresh/Beryl

refreshing-context

Use when the user asks to refresh, review, audit, or clean up the agent context files, periodically (for example monthly), or after a large change to the repository such as a restructure, migration, or major feature. Checks the context layer against the code, quizzes the developer to confirm what is still true, and removes or fixes redundant and misleading context with approval.

开发工程师
★ 11