CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sce-validate

Validate one completed SCE plan and record final validation evidence

Quality

75%

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 ./.claude/skills/sce-validate/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 a well-engineered control-flow document: strict step ordering, exhaustive outcome branching with explicit stops, preserved retry loops, and clean one-level-deep progressive disclosure into real, well-scoped reference files. Its only weaknesses are minor redundancy between the Rules and Workflow sections and the total delegation of concrete examples to references.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and assumes Claude's competence throughout, with no explanations of known concepts. However, the '## Rules' section restates branching already specified in the Workflow (e.g., 'On failed, print the handoff Markdown as returned and stop' duplicates the failed branch), and justificational asides like 'That property is load-bearing...' could be trimmed. This matches 'efficient; minor instances of over-explanation that could be trimmed' rather than the fully lean level 5.

4 / 5

Actionability

Guidance is concrete and executable: exact reference files per step, exhaustive branching on the three Status values with explicit stops, {plan-path}/{candidate-path} defined so every emitted command is directly runnable, and a named Completion layout in references/output.md. It stops short of level 5 only because the body itself contains no examples of the reports or layouts it mandates — all sample content lives in the references, leaving minor gaps if a reference were unavailable.

4 / 5

Workflow Clarity

A strict two-step sequence with read-before-run gates, explicit validation checkpoints (branch on blocked/failed/validated), feedback loops for error recovery (failed handoff ending in '/validate {plan-path}' retry), and explicit stop conditions for every outcome. This matches the anchor for a clear sequence with explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

The ~100-line body holds only control flow, with a table mapping each step to its reference file; all three referenced files (references/validation.md, references/validation-report.md, references/output.md) exist, are one level deep, and are clearly signaled with when to read them (including the point-in-time note for validation-report.md on validated/failed only). This matches the anchor for a clear overview with well-signaled one-level-deep references and easy navigation.

5 / 5

Total

18

/

20

Passed

Description

53%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 states a clear, terse 'what' with domain-specific vocabulary and low conflict risk, but it omits any 'when to use' trigger guidance and stops at two high-level actions. It is functional for dispatch but under-sells the skill's actual scope (full validation run, acceptance-criteria checks, Validation Report authoring).

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks to validate, verify, or run final checks on a completed SCE plan, or mentions /validate.'

Expand the 'what' with 2-3 more concrete actions, e.g. 'run the plan's full validation commands, verify each acceptance criterion, and write the Validation Report into the plan file.'

Include natural user phrasings and synonyms ('run validation', 'final check', 'verify the plan is done') to improve trigger-term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('SCE plan') and two concrete actions ('Validate one completed SCE plan', 'record final validation evidence'), but does not enumerate what validation covers (running full validation commands, checking acceptance criteria, writing the Validation Report). This matches the anchor for naming a domain with 1-2 concrete actions without comprehensive coverage, and falls short of the level 4 anchor requiring several specific actions.

3 / 5

Completeness

The 'what' is clear (validate a completed SCE plan, record final validation evidence), but there is no 'Use when...' clause or any equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 3. It cannot score 4 without at least an implicit 'when'.

3 / 5

Trigger Term Quality

Relevant keywords are present ('validate', 'validation', 'SCE plan', 'evidence'), but common natural variations a user would say ('run validation on', 'check the plan', 'is the plan done', 'final check') are missing. It has more than the one or two generic keywords of level 2, so level 3 fits best.

3 / 5

Distinctiveness Conflict Risk

'One completed SCE plan' and 'final validation evidence' carve a specific niche with distinct terminology, giving minor overlap risk only with closely related SCE workflow commands (e.g., a next-task or plan-execution skill). It lacks the explicit distinguishing trigger phrases of the level 5 anchor.

4 / 5

Total

13

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

crocoder-dev/shared-context-engineering

Path

.claude/skills/sce-validate/SKILL.md

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.