Skip to content
Skills Library
Programming · Testing

verification-before-completion

/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

Licence
MIT
Last repository change
27.07.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 27.07.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

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

Original author 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

How it works

  1. Overview
  2. The Iron Law
  3. The Gate Function
  4. Agent-Filed Bead Discipline
  5. Common Failures
  6. If Verification Cannot Run
  7. Red Flags - STOP
  8. Rationalization Prevention
  9. Key Patterns
  10. When To Apply
Original SKILL.md headings · 177 lines, 1,166 words
SKILL.md preview
---
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
---

# 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
6. CLOSE: If this verification gates a bead closure, run `bd close <id> --reason "description with evidence from step 4"`

Skip any step = lying, not verifying
```

## Agent-Filed Bead Discipline

When a skill **files a bead for discovered/follow-up work** (not planned work), stamp it so a human can triage risk at a glance.

- **Title:** prefix `[spec]` ONLY if speculative. Confirmed beads keep clean titles.
- **Body/notes — always include this 3-field stamp:**
  ```
  Severity: Critical | Important | Minor
  Confidence: Confirmed | Speculative
  Evidence: <file:line / failing test / repro>   (or: none)
  ```
- **Mechanical rule:** evidence cited → `Confidence: Confirmed`; no evidence → `Confidence: Speculative`. Applies at all severities. **Never blocks filing** (surface-and-mark — Production-Grade Doctrine).
- **What counts as evidence** (claim-substantiating AND checkable, not "a string exists"):
  - ✅ `parser.ts:142 — returns null on empty input (fails t_parse_empty)`
  - ❌ `parser.ts — looks wrong`
- **High-severity nudge:** a `Critical`/`Important` bead filed without evidence MUST add one line: `Why this severity w/o evidence: <reason>`.
- **Priority (`-p`) stays human-owned** — do not infer priority from severity.
- **Honest limit:** this disciplines the instruction surface, not every runtime bead. `Confidence: Confirmed` is a falsifiable triage hint that lowers verification cost, not proof. The convention is forward-only — pre-existing beads stay unstamped.

## 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 |
| No security regression | SAST/audit tool if one exists (semgrep, bandit, npm/pip audit) → 0 new findings, AND diff review: no control weakened/removed/bypassed, no new sink. No tool? Use the "If Verification Cannot Run" path: record the manual diff-review as evidence, note no SAST available. | Tests pass (tests rarely cover security) |

## If Verification Cannot Run

When no verification command exists (no test suite, CI down, external dependency unavailable):

1. **Record the gap:** `bd note <id> "verification blocked: <reason>"`
2. **Create a blocker:** `bd create "Set up verification for <feature>" -t task` and `bd dep add <current-task> <new-task>`
3. **Document partial verification:** Note what WAS verifiable (e.g., "linter passes, manual smoke test done, but no automated test suite exists")
4. **Never silently skip:** A bead closed without verification evidence AND without a documented gap is worse than a bead left open

## 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"
- About to claim done while a requirement was quietly dropped, or a security regression remains unverified (tests passing ≠ security verified)
- 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 |
| "It's good enough to ship" | Production system, real users — no shortcut, no dropped requirement, no accepted security regression |
| "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

## Beads Completion

`bd close` without fresh verification evidence is lying. Before closing any bead:
1. Run the verification command that proves the work is done
2. Annotate the bead with evidence: `bd note <id> "test output: 14 passed, 0 failed"`
3. Include the summary in the `--reason` flag
4. Only then execute `bd close`

Use `bd note` to attach detailed evidence (test output, diff stats, verification logs) to the bead before closing. The `--reason` flag is the summary; `bd note` is the full evidence trail.

A bead closed without evidence is worse than a bead left open — it corrupts the ledger.

**Capture what you learned.** At close, record durable, evidence-backed insights (still true next month, tied to a file, test, or command). Never record guesses, one-offs, or secrets (tokens, keys, PII — every memory is injected into all future sessions). Update in place (`bd remember --key <key>`) rather than adding a near-duplicate.

```bash
bd remember "<kind>: <durable, evidence-backed insight>"   # kind: lesson / pattern / design / root-cause / research
```

## Integration

**Invoked by:** Any task claiming completion — mandatory before `bd close`, commits, or PRs.

**Pairs with:**
- **systematic-debugging** — verify the fix worked before claiming success.
- **document-release** — docs audit is part of completion evidence.
- **write-documentation** — prose quality checks are completion evidence.
- **stress-test** — stress-test validates designs; this skill validates implementations.

Versions

RepositoryScoreLicence
This page · dollardill/beads-superpowers100MIT
jjuraszek/pi-gauntlet100MIT
GanyuanRan/Aegis100MIT
mvschwarz/openrig100Apache-2.0
nikospavlopoulos/devops-mutant-powers100MIT
FrancoStino/opencode-skills-collection100MIT
foryourhealth111-pixel/Vibe-Skills100Apache-2.0
rootcastleco/rei-skills100MIT
Montinou/triqual100MIT

Database snapshot: 13.11.2026 · package version 828be3dbfb54 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100verifying-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
  • 90sp-verify
    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
  • 100verify
    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.
  • 100verify
    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
  • 100sr-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
  • 100ferrox-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

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.