ahgraber/spec-kit-analyze
skills/spec-kit-analyze/SKILL.md
Use when `spec.md`, `plan.md`, and `tasks.md` exist and you need a read-only Spec Kit audit for consistency, requirement-to-task coverage, ambiguity, duplication, or constitution conflicts before implementation.
$ install --global
skillsauthnpx skillsauth add ahgraber/skills spec-kit-analyzeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 10, 2026, 3:10 AM9.5s3 files scanned
SKILL.md
- name:
- spec-kit-analyze
- description:
- |-
Spec Kit Analyze
Run a non-destructive cross-artifact quality audit before implementation.
Invocation Notice
- Inform the user when this skill is being invoked by name:
spec-kit-analyze.
When to Use
tasks.mdexists and you want a pre-implementation consistency check across spec/plan/tasks.- You suspect coverage gaps, requirement drift, ambiguous language, or contradictory artifacts.
- You need a constitution-alignment gate without editing artifacts yet.
When Not to Use
- Any prerequisite artifact is missing (
spec-kit-specify,spec-kit-plan, orspec-kit-tasksfirst). - You need targeted remediation edits now (
spec-kit-reconcile). - You are executing implementation work (
spec-kit-implement).
Router Fit
- Primary route from
spec-kitafterspec-kit-tasks. - Read-only quality gate before
spec-kit-implement. - Default handoff to
spec-kit-reconcilewhen findings require coordinated artifact updates.
Critical Constraints
- Strictly read-only: do not modify files.
- Treat
memory/constitution.mdas authoritative; any MUST-level conflict isCRITICAL.
Preconditions
- Run from repository root (or a subdirectory inside it).
- Active feature context resolves to one feature directory with
spec.md,plan.md, andtasks.md.
Workflow
-
Resolve artifact paths and enforce prerequisite gate:
- Run
scripts/check-prerequisites.sh --json --require-tasks --include-tasksexactly once. - Parse:
FEATURE_DIRAVAILABLE_DOCS
- Derive:
SPEC = FEATURE_DIR/spec.mdPLAN = FEATURE_DIR/plan.mdTASKS = FEATURE_DIR/tasks.md
- If any required artifact is missing, stop and route to the owning sibling skill.
- Run
-
Load focused sections from:
spec.md: requirements, stories, acceptance criteria, edge cases.plan.md: architecture/stack decisions, phases, constraints.tasks.md: task IDs, phase grouping,[P]markers, referenced paths.memory/constitution.md: principle names and normative MUST/SHOULD statements.
-
Build internal maps:
- Requirement inventory (functional + non-functional) with stable keys.
- Story/action inventory with acceptance-test intent.
- Task-to-requirement/story coverage mapping.
- Constitution obligations relevant to spec/plan/tasks scope.
-
Detect and classify issues:
- Duplication: overlapping or near-duplicate requirements.
- Ambiguity/placeholders: vague quality terms, TODO/TKTK/placeholder tokens.
- Underspecification: requirements lacking measurable outcomes or clear objects.
- Constitution conflicts: violations against MUST principles (
CRITICAL). - Coverage gaps: requirements without tasks and tasks without mapped requirement/story.
- Cross-artifact inconsistency: terminology drift, entity mismatch, ordering contradictions.
- Cap findings at 50 rows; summarize overflow counts by category.
-
Assign severity and output a compact report with stable IDs, coverage table, and metrics.
CRITICAL: constitution MUST violations, missing core coverage that blocks baseline behavior.HIGH: conflicting/duplicate requirements, untestable or high-risk ambiguity.MEDIUM: terminology drift, non-functional coverage gaps, underspecified edge cases.LOW: wording/style cleanup without execution impact.
-
Recommend next actions:
- If
CRITICAL/HIGHfindings require cross-artifact edits, blockspec-kit-implementand route tospec-kit-reconcilewith a concise gap summary. - If only one artifact needs focused updates, route to its owner skill (
spec-kit-specify,spec-kit-plan, orspec-kit-tasks). - Otherwise provide prioritized improvements and whether implementation can proceed.
- If
-
Offer follow-up only:
- Ask whether to run
spec-kit-reconcileusing top findings as the gap report. - Do not apply any edits in this skill.
- Ask whether to run
Output
- Markdown report only (no file writes) containing:
- Findings table:
ID | Category | Severity | Location(s) | Summary | Recommendation - Requirement coverage table:
Requirement Key | Has Task? | Task IDs | Notes - Constitution alignment issues (if any)
- Unmapped tasks (if any)
- Metrics:
- Total requirements
- Total tasks
- Coverage percentage
- Ambiguity count
- Duplication count
- Critical issues count
- Next-step routing recommendation
- Findings table:
References
references/command-analyze.mdscripts/check-prerequisites.shhttps://github.com/github/spec-kit/blob/9111699cd27879e3e6301651a03e502ecb6dd65d/templates/commands/analyze.md
Related Skills
ahgraber/editorial-review
development
VerifiedTrustedCommunity
Use when the user wants rigorous, non-sycophantic editorial feedback on a draft, essay, blog post, or argument through back-and-forth dialogue — pressure-testing thesis, structure, argument, clarity, tone, and evidence. Triggers: "be my sparring partner", "pressure-test this draft", "poke holes in my argument", "is this ready to publish", "sharpen this post", "where is this weak". Not for one-shot copyediting, proofreading, or ghostwriting.
2SKILL.mdUpdated May 26, 2026
ahgraber/synthesize
testing
VerifiedTrustedCommunity
Use when distilling the through-line gist of one or more sources — the spine, argument, tension, or recurring frame running through a set of documents, notes, research, or transcripts, OR across the ideas within a single rich piece — into a few concise paragraphs. Triggers: "synthesize", "what's the through-line/gist", "extract the insight", "pull these together". Not for faithful summary or condensation that covers what a source says, nor for comparisons or catalogs where enumeration is the deliverable.
2SKILL.mdUpdated May 22, 2026
ahgraber/writing-tests
development
VerifiedTrustedCommunity
Use when writing or reviewing tests in any language, or diagnosing a suite that is slow, brittle, or hard to read. Triggers: "write tests", "how should I test this", "what kind of test", "test is flaky/fragile", "should I mock this", "test is hard to read". For Python-specific guidance see `python-testing`.
2SKILL.mdUpdated May 16, 2026
ahgraber/strudel
development
VerifiedTrustedCommunity
Use when writing, debugging, or explaining Strudel live-coding music patterns — mini-notation syntax, pattern functions (fast/slow/every/off/stack), synth/sample selection, audio effects, scale/chord/voicing API, or EDM production recipes. Triggers: "write a Strudel pattern", "how do I make a bassline in Strudel", "what does .every() do", "strudel drum beat", "strudel chord voicing", any Strudel code question.
2SKILL.mdUpdated May 16, 2026