CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

The canonical home for this skill is spec-planning in tdg-ninja/context-specs-factory-ai

SKILL.md
Quality
Evals
Security

Quality

Content

78%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.

A thorough, highly actionable skill body with concrete templates, exact paths, and well-sequenced workflows including idempotency and crash-recovery checkpoints; its main weaknesses are minor verbose prose and a long inlined context-engineering section that borders on monolithic.

DimensionReasoningScore

Conciseness

The body is mostly efficient and dense with concrete patterns, but the philosophical 'Spec-Driven Development & Your Role' paragraph and a few restated guidelines could be trimmed; it sits between 'mostly efficient with some unnecessary explanation' (3) and 'efficient; minor over-explanation' (4).

3.5 / 5

Actionability

Provides copy-paste-ready templates and exact commands — the completion protocol ('git add ... commit ... push ... touch sentinel'), the Slice Dependency Map table, the Signal section format, slice naming ('1.1-type-contracts.md'), and concrete BEFORE/AFTER and type-contract examples cover the common cases fully.

5 / 5

Workflow Clarity

The Invocation Contract gives a clearly ordered completion protocol plus explicit idempotency, crash-recovery, and ambiguous-PRD checkpoints with feedback loops, but the happy path lacks an explicit 'verify mainspec/slices are complete before committing' checkpoint between writing and the first push.

4 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep references to references/experts.md and references/signals.md (both present on disk), though the inlined six-pattern Context Engineering section is long and could partly live in a reference file.

4 / 5

Total

16.5

/

20

Passed

Description

63%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.

A highly specific, concrete description that clearly defines what the skill does and the artifacts it touches, but it omits any explicit 'when to use' trigger guidance and leans on internal pipeline jargon over natural user phrases.

Suggestions

Add an explicit 'Use when ...' clause naming natural trigger phrases (e.g., 'Use when turning a PRD into a spec plan, or when planning slices for a new feature').

Soften internal jargon in the trigger surface — keep 'PRD' and 'spec plan' as the user-facing keywords and relegate 'run-prd-test.sh' / '.planning-done' to the body.

Add a one-line 'when' framing that distinguishes this from the sibling spec-validate skill to further reduce overlap risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions with exact paths — 'Reads a PRD (`prds/<feature>/prd.md`)', 'produces `specs/<feature>/mainspec.md` plus dependency-ordered slices', 'Encodes the runner as a slice success criterion', 'Touches `specs/<feature>/.planning-done`' — comprehensive and specific rather than vague.

5 / 5

Completeness

The 'what' is clearly and concretely answered, but there is no 'Use when...' clause or equivalent explicit trigger guidance — per the rubric, a missing 'when' caps completeness at 3 even though the what is strong.

3 / 5

Trigger Term Quality

Relevant domain keywords like 'PRD', 'spec', 'mainspec', and 'slices' appear, but much of the language is internal pipeline jargon ('run-prd-test.sh', '.planning-done') and common natural synonyms or variations a user might say are missing.

3 / 5

Distinctiveness Conflict Risk

The PRD→mainspec→slices→sentinel pipeline is a distinct niche with minimal conflict risk, though it shares the 'spec' surface with the sibling spec-validate skill mentioned in the body, giving minor overlap risk rather than a fully isolated niche.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tdg-ninja/context-specs-claude-code
Reviewed

Table of Contents

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.