Skip to content
Back to skills

Verifying Completion

ASecurity

Verify completion claims with evidence before commit.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 16, 2026
developmentrustgoshellexpressgit

Security analysis

A100/100

Scanned November 16, 2026

npx -y skills add Acendas/shipyard --skill verifying-completion --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Verifying Completion?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Verifying Completion
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/acendas-verifying-completion/badge)](https://www.skillsdirectory.com/skills/acendas-verifying-completion)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: verifying-completion
description: Verify completion claims with evidence before commit.
disable-model-invocation: true
---

# Verifying Completion

A task is "done" only when its acceptance is observable — right now, in this turn, with output you read. Internal confidence, prior runs, and "it should work" are not evidence.

## The Iron Law

```
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
```

No completion claim is permitted unless the verification command ran in this message. Period.

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

## The Gate Function

Before flipping a task to `done`, marking a sprint complete, approving a feature, or asserting any "X works" / "tests pass" / "fixed" / "ready" — run this gate:

```
1. IDENTIFY: What command, in this exact moment, proves the claim?
2. RUN:      Execute the FULL command from a clean state (fresh shell, fresh build).
3. READ:     Read the FULL output. Capture exit code. Count failures.
4. VERIFY:   Does the output literally confirm the claim?
                YES → state the claim WITH the evidence inline (last 10 lines + exit).
                NO  → state actual status with the evidence; do NOT claim done.
5. ONLY THEN: Make the claim or flip the marker.

Skipping any step = lying, not verifying.
```

## Claim → Evidence Map

| Claim | Required evidence | Insufficient |
|---|---|---|
| Tests pass | Test command output: `0 failed`, exit 0, run in this turn | "Last run was green" / "should pass" |
| Fix works | Acceptance probe exit 0 with observable output proving wiring | "Code looks right" / "compile clean" |
| Bug fixed | The original failing test or repro now passes; ran in this turn | "Code changed; assumed fixed" |
| Build succeeds | Build command exit 0 in this turn | Linter passing / "no syntax errors" |
| Linter clean | Lint command output: `0 errors` in this turn | Partial check / extrapolation |
| Regression test added | Red→Green→Revert→Red→Restore→Green cycle observed | "Test passes once" |
| Subagent completed task | Subagent's structured return AND `git log` shows commit AND probe ran | Subagent reply alone |
| Acceptance scenario implemented | Scenario maps to a passing test case AND the demo path runs end-to-end | Code resembles the scenario |
| Sprint complete | All tasks `done` AND full test suite passed in this turn AND review verdict captured | Each task individually green at its own time |
| Spec compliance | Each acceptance criterion has a probe/test result in this turn | "Reviewer scanned the diff" |

## Red Flags — Stop Immediately

If any of these are true, you are about to claim done without verification:

- Using "should", "probably", "looks like", "seems to"
- Expressing satisfaction before running the check ("Great!", "Perfect!", "Done!")
- About to commit, push, or transition status without running the verifier in this turn
- Trusting a subagent's return claim without confirming via `git log` and the captured probe output
- Marking a checkbox `[x]` based on the previous iteration's evidence
- Thinking "just this once" or "the test is flaky anyway"
- Tired and wanting work over

When you notice any of these, **stop, run the verifier, then proceed with real evidence**.

## When to Apply

**Always before:**
- Any variation of success / completion / "ready" / "done" / "fixed" / "passing" claims
- Flipping a task `status` to `done`, a feature to `done`, a sprint to `completed`
- Committing with a `feat:` / `fix:` / `chore:` message that asserts completion
- Marking `[x]` on any progress checkbox or action item
- Approving in `/ship-review`
- Returning `STATUS: COMPLETE` from a subagent
- Any user-facing message implying the work is finished

**The rule applies to:**
- Exact phrases ("tests pass", "fixed", "done")
- Paraphrases ("everything looks good", "all green", "ready to ship")
- Implications ("wrapping up Wave 2")
- Status transitions in any tracked artifact (step file, sprint file, action items file)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in development →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.