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 ./.agents/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-structured orchestration document: it owns control flow, delegates phase detail to appropriately split references, and defines explicit gates, stops, and a retry loop. Minor duplication between the Workflow section and Rules is the only trimming opportunity.

DimensionReasoningScore

Conciseness

The body is a lean control-flow document with no padding or explanations of known concepts, but there is minor duplication: the read-the-reference-first rule appears in both 'Phase references' and 'Rules', and the non-repairing boundary is stated in step 1 and again in Rules. That repetition keeps it at anchor 4 rather than 5.

4 / 5

Actionability

Guidance is concrete and executable for an instruction-only skill: an explicit dispatch table, exact status branches ('blocked', 'failed', 'validated') each with a defined action and stop, input handling rules, and a concrete example ('$sce-validate my-plan'). It stops short of anchor 5 only because the executable validation detail is delegated to references rather than fully self-contained.

4 / 5

Workflow Clarity

The sequence is explicit with validation gates throughout: branch-on-Status checkpoints, hard stops per outcome, a blocked guard when implementation tasks remain, and a fix-then-rerun feedback loop preserving the '/validate {plan-path}' retry instruction on failure. This matches the 'clear sequence with explicit validation steps and feedback loops' anchor.

5 / 5

Progressive Disclosure

SKILL.md is a control-flow overview that splits phase detail into three real, directly-referenced files (references/validation.md, references/validation-report.md, references/output.md), each signaled with when to read it ('Read the reference before taking any action for step 1'; validation-report.md is pointed to 'at the moment it is needed'). All references are one level deep and every referenced path exists in the bundle, matching the clear-overview anchor.

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 is concise and states a clear, specific purpose, but it omits any 'when to use' trigger guidance and lacks natural keyword variations. It reads as a capability statement rather than a discovery surface for a skill invocation.

Suggestions

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

Include natural trigger variations users would say — 'validate the plan', 'check the plan', 'run final validation' — to improve trigger_term_quality.

Mention the concrete actions the phase performs (run full validation commands, check acceptance criteria, write the Validation Report) to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions — 'Validate one completed SCE plan' and 'record final validation evidence' — matching the '1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because it does not list several specific actions (no mention of running validation commands, checking acceptance criteria, or writing a report).

3 / 5

Completeness

It clearly answers 'what' (validate a completed SCE plan and record evidence) but contains no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not a 2 because the 'what' is clear and specific rather than vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ('Validate', 'SCE plan', 'validation evidence') but common variations users would naturally say are missing ('check the plan', 'verify the plan', 'final check', 'plan done'). It clears anchor 3 ('some relevant keywords but missing common variations') without reaching anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The niche is clear — final validation of a completed SCE plan — making it mostly distinct with only minor overlap risk against sibling SCE workflow skills and generic 'validate' phrasing. Not a 5 because 'Validate' alone could collide with non-SCE validation requests, and the description does not carry fully distinct trigger phrases.

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

.agents/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.