spec-planning

Reads a PRD (`prds/<feature>/prd.md`) plus its executable `run-prd-test.sh` (and any helper artifacts under `prds/<feature>/`), grounds them in codebase research, and produces `specs/<feature>/mainspec.md` plus dependency-ordered slices. Encodes the runner as a slice success criterion so implementation completion implies `./prds/<feature>/run-prd-test.sh` exits 0. Touches `specs/<feature>/.planning-done` as its final committed action. Agent-first — no human-in-the-loop.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/sdd/spec-planning/SKILL.md

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and well-sequenced with explicit validation and recovery logic, structured into clear sections with one-level-deep references. Its main weakness is that the referenced catalogs are empty stubs, slightly undermining the progressive-disclosure navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence — concrete paths, commands, and templates rather than concept explanations — with only minor over-explanation in the prose 'Spec-Driven Development & Your Role' paragraph that reiterates the Guidelines.	4 / 5
Actionability	Provides copy-paste-ready templates and commands throughout — the invocation contract (`claude -p "/spec-planning <feature>"`), the numbered completion protocol with exact git/touch commands, BEFORE/AFTER code blocks, type contracts, and the Signal section and Slice Dependency Map formats.	5 / 5
Workflow Clarity	The completion protocol is an explicit ordered checklist with validation checkpoints — idempotency ('If .planning-done already exists, exit'), crash recovery ('verify the existing artifacts are complete and self-consistent, fix any gaps'), and an ambiguous-PRD feedback loop (write clarifications-needed.md, exit, dispatcher re-fires).	5 / 5
Progressive Disclosure	Clear sectioned structure with one-level-deep references clearly signaled ('MUST Read the experts catalog at START of planning: references/experts.md'); the gap is that experts.md and signals.md are empty stubs, and the inlined Context Engineering patterns (~150 lines) could arguably live in a reference file.	4 / 5
	Total	18 / 20 Passed

Description

56%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is highly specific about what the skill does and occupies a distinct niche, but it omits any 'Use when...' trigger guidance and leans on internal jargon rather than natural user phrases, capping completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when turning a PRD into a spec plan / dependency-ordered implementation slices, or when the user asks for spec-driven planning.'

Add natural-language synonyms users actually say ('spec plan', 'break a feature into slices', 'plan implementation from a PRD') alongside the technical terms.

Spell out jargon like 'PRD' and 'sentinel' on first use so the description is parseable without project context.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Reads a PRD', 'grounds them in codebase research', 'produces specs/<feature>/mainspec.md plus dependency-ordered slices', 'Encodes the runner as a slice success criterion', 'Touches specs/<feature>/.planning-done' — covering the full pipeline comprehensively.	5 / 5
Completeness	The 'what' is clear and detailed, but there is no 'when' — no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords are almost entirely internal jargon ('PRD', 'run-prd-test.sh', 'mainspec.md', 'slice success criterion', '.planning-done', 'Agent-first') with no 'Use when...' clause and none of the natural phrases a user would actually say; only 'spec' and 'PRD' approach relevance.	2 / 5
Distinctiveness Conflict Risk	It carves a clear niche (PRD → mainspec + dependency-ordered slices with a test-runner success criterion) that is unlikely to collide with unrelated skills, though the lack of explicit triggers leaves minor overlap risk with general planning/spec skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tdg-ninja/context-specs-factory-ai
Path: skills/sdd/spec-planning/SKILL.md
Commit: 3a7a725

Reviewed: about 19 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.