AGENT SKILL

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires current fingerprint-bound verification evidence; respects workflow-owned validation epochs instead of duplicating commands.

License 许可
MIT
最近更新
2026-08-07
Stars
★ 0
Forks
0

01 前言 Front Matter

name
verification-before-completion
metadata
{ "author": "github-spec-kit", "source": "templates/passive-skills/verification-before-completion/SKILL.md" }
description
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs. Requires current fingerprint-bound verification evidence; respects workflow-owned validation epochs instead of duplicating commands.
compatibility
Requires spec-kit project structure with .specify/ directory

03 SKILL.md 正文

Verification Before Completion

Overview

Claiming work is complete without verification is dishonesty, not efficiency.

Core principle: Evidence before claims, always.

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

Workflow-Owned Validation

When an active workflow provides a validation epoch ledger, fresh evidence means current source-fingerprint-bound evidence in that ledger. Inspect it before a claim. Only the workflow's Leader may open a missing heavyweight epoch, and only when budget remains. A worker, passive skill, join, resume, or message must not start an extra validation epoch merely to make a local claim.

For sp-implement, moving to the next Txx does not require another heavyweight test run. Record cheap task checks and test impact, then let the Leader verify the integrated change-set. The budget remains shared across Implement and Review and must not be reset at handoff.

The Iron Law

NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE

If the current source fingerprint has no accepted verification evidence, you cannot claim it passes. Evidence may come from the active workflow's canonical epoch ledger; it need not be rerun in this message.

The Gate Function

BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN OR REUSE: Outside a workflow budget, execute the full proving command.
   Inside one, reuse a passed epoch for the unchanged fingerprint or ask the
   Leader to allocate the next epoch; do not run independently.
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 Current-fingerprint command output or accepted epoch evidence: 0 failures Stale 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 current verification evidence

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"

Standalone regression tests (TDD Red-Green):

✅ Outside an epoch-owned workflow: Write → Run (pass) → Revert fix → Run
(MUST FAIL) → Restore → Run (pass)
✅ Inside an epoch-owned workflow: use its recorded change-set RED and integrated
GREEN evidence; do not manufacture three extra runs.
❌ "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

Why This Matters

From 24 failure memories:

  • your human partner said "I don't believe you" - trust broken
  • Undefined functions shipped - would crash
  • Missing requirements shipped - incomplete features
  • Time wasted on false completion → redirect → rework
  • Violates: "Honesty is a core value. If you lie, you'll be replaced."

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
  • Final workflow or delivery claims that are not already covered by current fingerprint-bound epoch evidence

Rule applies to:

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

The Bottom Line

No shortcuts for verification.

Run the command when you own the gate, or inspect the canonical current epoch when the workflow owns it. Read the evidence. Then claim only what it proves.

This is non-negotiable.

04 同仓库更多 Skills

chenziyang110
chenziyang110/launchdeck

launchdeck-agent

Codex host adapter contract fixture for Launchdeck.

★ 0
chenziyang110
chenziyang110/launchdeck

launchdeck-agent

Claude host adapter contract fixture for Launchdeck.

★ 0
chenziyang110
chenziyang110/launchdeck

launchdeck-agent

Use this skill aggressively for local project lifecycle operations even when the user does not mention Launchdeck: start this project, run the dev server, dev, build, test, restart service, stop service, show logs, inspect ports, port is occupied, clean cache; and when the user explicitly asks to configure this local project for Launchdeck or create or generate a project-adapted `.launchdeck.yml`, including 为这个项目生成 Launchdeck 配置. Do not use for ordinary code edits, docs-only work, general explanations, API design discussion, or production deployment unless the user also asks to operate or configure a local project or service.

★ 0
chenziyang110
chenziyang110/launchdeck

zig-testing

Use ONLY when user explicitly requests Zig test code, built-in test runner configuration, test failure diagnosis, or coverage for Zig projects. Triggers: "write test zig", "zig test", "testing.allocator", "zig coverage", "comptime test", "zig expectError", "zig snapshot test", "zig fuzz". Do NOT activate for: general Zig coding without test context, build.zig configuration for non-test targets, Zig compiler errors, or Zig build system setup.

★ 0
chenziyang110
chenziyang110/launchdeck

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.

★ 0
chenziyang110
chenziyang110/launchdeck

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

★ 0