CtrlK
BlogDocsLog inGet started
Tessl Logo

spec-validate

Validates a mainspec and its slices via 3-subagent consensus plus expert review, then *applies* impactful fixes directly to the spec files. No human-in-the-loop summary or approval — agent-first. Touches `specs/<feature>/.validated` as its final committed action.

59

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is a well-sequenced, highly actionable orchestration workflow with clear checkpoints, weakened mainly by a redundant Notes section and minor schematic placeholders in the spawn examples.

Suggestions

Remove or fold the 'Notes' section into the relevant phases to eliminate restated content and recover token budget.

Replace the schematic placeholders in the Task() blocks ('[Validation prompt below ...]', '[Identical prompt]') with concrete cross-references so the spawn guidance is fully executable.

Consider adding a brief post-edit verification step (e.g. re-reading edited slices for consistency) before the final commit/push to strengthen the feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly efficient, but the closing 'Notes' section restates points already covered in the phases ('Always 3 subagents', 'Model: opus', 'Foreground parallel execution', 'Consensus = confidence') and could be trimmed.

3 / 5

Actionability

It provides concrete, executable guidance — verbatim Task() spawn blocks, the full validation prompt, a git commit/push sequence, and a validation-log template — but the Task blocks use schematic placeholders ('[Validation prompt below with spec content inserted]', '[Identical prompt]') rather than fully copy-paste-ready text.

4 / 5

Workflow Clarity

The workflow is clearly sequenced (Invocation Contract completion protocol + Phases 1-2-3 with substeps 3a-3f) with explicit checkpoints (idempotency exits, consensus threshold table, impactful/nitpick classification), though there is no post-edit verification step before the commit/push.

4 / 5

Progressive Disclosure

No bundle files are present and the skill is self-contained; sections are well-organized with clear headers, though some inline boilerplate (the validation prompt and log template) could optionally live in referenced files.

4 / 5

Total

15

/

20

Passed

Description

67%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 specific and clearly distinct, but it omits explicit trigger/when guidance and leans heavily on internal jargon rather than natural user phrases.

Suggestions

Add an explicit 'Use when ...' clause stating when this skill should be invoked (e.g. 'Use when validating a feature mainspec and its slices before implementation').

Replace or supplement jargon ('mainspec', 'slices', 'sentinel') with natural terms a user or dispatcher would recognize to improve trigger-term quality.

Include common synonyms/file extensions or phrasings users might say when they need spec validation.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Validates a mainspec and its slices via 3-subagent consensus plus expert review', 'applies impactful fixes directly to the spec files', 'Touches specs/<feature>/.validated as its final committed action' — giving comprehensive, specific coverage rather than vague language.

5 / 5

Completeness

It clearly answers 'what' (validate via consensus + expert review, apply fixes, write sentinel) but provides no explicit 'Use when...' or equivalent trigger guidance, so per the rubric cap completeness stays at 3.

3 / 5

Trigger Term Quality

It includes a couple of relevant keywords ('validate', 'spec', 'fixes') but the bulk is internal jargon ('mainspec', 'slices', 'sentinel', 'dispatcher', '3-subagent consensus') rather than the natural phrases a user would say, and no common synonyms are covered.

3 / 5

Distinctiveness Conflict Risk

It occupies a clear niche (spec validation with consensus + sentinel-based completion) with distinct triggers and minimal overlap risk versus adjacent skills like spec-planning.

5 / 5

Total

16

/

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.