agentleFS
jaroslawherodjaroslawherod/micold-ai-ide/.claude/skills/speckit-bugfix-verify/SKILL.md

speckit-bugfix-verify

Skill1 starsChanged 3 days agoApache-2.0View on GitHub

Verify that bugfix patches are consistent across all spec artifacts

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify that all spec artifacts are consistent after bugfix patches — checks that new requirements have corresponding plan sections and …

    line 19
  2. Very specific:

    Verify a spec-kit project exists by checking for .specify/ directory

    line 31
  3. Very specific:

    Verify at least spec.md exists

    line 33
  4. Distinctive:

    Load all artifacts: Read from the current feature directory:

    line 37
  5. Distinctive:

    No duplicate requirements introduced by the patch

    line 54
  6. Distinctive:

    Every new requirement in spec.md has a corresponding plan section or note

    line 58
  7. Distinctive:

    No plan sections reference removed or superseded requirements

    line 59
  8. Distinctive:

    Every new requirement in spec.md is traceable to at least one task

    line 63
  9. Very specific:

    No tasks marked [x] that were supposed to be reopened

    line 64

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Bugfix Verify Skill

Verify Bugfix Consistency

Verify that all spec artifacts are consistent after bugfix patches — checks that new requirements have corresponding plan sections and tasks, reopened tasks are not still marked complete, and no orphaned references exist.

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty). The user may specify a bug ID to verify (e.g., "BUG-001") or "all" to check everything.

Prerequisites

  1. Verify a spec-kit project exists by checking for .specify/ directory
  2. Locate the current feature's spec directory
  3. Verify at least spec.md exists

Outline

  1. Load all artifacts: Read from the current feature directory:
    • spec.md — the source of truth
    • plan.md — implementation plan (if exists)
    • tasks.md — task breakdown (if exists)
    • specs/{feature}/bugs/*.md — all bug reports
  2. Check bug report status: For each bug report file:

    CheckPass ConditionFail Condition
    Report existsBug file is in bugs/ directoryMissing bug file
    Report is patchedHas **Status**: Patched markerStill Open or missing status
    Patch date presentHas **Patched**: [DATE] entryMissing patch date
  3. Verify spec.md consistency: For each bugfix note in spec.md:
    • New requirements have clear acceptance criteria
    • Strikethrough items have a reason documented
    • No duplicate requirements introduced by the patch
    • Bug IDs in notes match existing bug report files
  4. Verify plan.md consistency (if exists):
    • Every new requirement in spec.md has a corresponding plan section or note
    • No plan sections reference removed or superseded requirements
    • Bugfix notes in plan.md match those in spec.md
  5. Verify tasks.md consistency (if exists):
    • Every new requirement in spec.md is traceable to at least one task
    • No tasks marked [x] that were supposed to be reopened
    • Reopened tasks have the (reopened — BUG-NNN) annotation
    • New task IDs are sequential and do not duplicate existing IDs
    • Task dependencies form a valid DAG (no circular dependencies)
    • Wave DAG (if present) includes all new tasks
  6. Output verification report:

    # Bugfix Verification Report
    
    **Feature**: [Feature name]
    **Date**: [DATE]
    
    ## Bug Reports
    | Bug ID | Title | Status | Patched |
    |--------|-------|--------|---------|
    | BUG-001 | [Title] | ✅ Patched | [DATE] |
    | BUG-002 | [Title] | ⚠️ Open | — |
    
    ## Consistency Checks
    
    | Check | Result | Details |
    |-------|--------|---------|
    | All bugs patched | ✅ Pass / ⚠️ Fail | [N patched, M open] |
    | Spec requirements covered | ✅ Pass / ⚠️ Fail | [N requirements, all have tasks] |
    | No false completions | ✅ Pass / ⚠️ Fail | [N tasks verified] |
    | Reopened tasks annotated | ✅ Pass / ⚠️ Fail | [N reopened, all annotated] |
    | Task IDs sequential | ✅ Pass / ⚠️ Fail | [Last ID: TNNN] |
    | No circular dependencies | ✅ Pass / ⚠️ Fail | [DAG valid] |
    | Cross-artifact traceability | ✅ Pass / ⚠️ Fail | [All specs → plan → tasks] |
    
    ## Recommended Actions
    - [List any issues found and how to fix them]
    - If all checks pass: Resume `/speckit.implement` to apply the code fix
  7. Report: Output the verification report. Do not modify any files — this command is read-only.

Rules

  • Read-only — this command never modifies any files
  • Check all artifacts — verify consistency across spec, plan, tasks, and bug reports
  • Be specific about failures — report exact bug IDs, task IDs, and requirement text that fail checks
  • Handle missing artifacts gracefully — if plan.md or tasks.md does not exist, skip those checks and note the absence
  • Verify traceability — every bugfix note must reference a valid bug report, and every bug report must have corresponding artifact changes

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.