CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sce-decision

Record one already-qualified decision as an immutable ADR, reusing an equivalent active ADR when present

Quality

80%

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 ./.pi/skills/sce-decision/SKILL.md

The canonical home for this skill is sce-decision in crocoder-dev/shared-context-engineering

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 an exemplary instruction-only skill contract: fully concrete path, status, slug, and result-field specifications, a clearly sequenced workflow with an explicit verification step and error-recovery semantics, and correct delegation of the ADR schema to a single well-signaled reference file. The only improvement opportunity is mild redundancy from constraints restated across multiple sections.

DimensionReasoningScore

Conciseness

The body is dense, directive, and free of concept explanations Claude already knows, but several constraints repeat across sections — immutability appears in steps 2 and 5 and Boundaries, and caller-ownership is stated in Purpose, Qualification handoff, step 4, and step 6 — so some trimming is possible, fitting anchor 4 rather than 5.

4 / 5

Actionability

As an instruction-only skill the guidance is fully concrete: the exact path pattern 'context/decisions/YYYY-MM-DD-<decision-slug>.md', the exact allowed status vocabulary, slug and collision policy, and exact enumerated result fields for every outcome ('status, adr_path, decision, decision_status, created, supersedes, verification'), with the ADR schema delegated by name to a real file.

5 / 5

Workflow Clarity

Six clearly sequenced steps include an explicit verification checklist in step 5 ('no existing ADR was modified') and error-recovery feedback via the 'blocked' result with 'problem', 'impact', and 'required_action', plus well-defined non-blocking outcomes — matching the anchor with validation steps, feedback loops, and a checklist.

5 / 5

Progressive Disclosure

A single one-level-deep reference ('references/adr-template.md', which exists) is clearly signaled as 'the sole authority for the persisted ADR schema', and the template content is appropriately kept out of the body ('do not restate or invent a parallel section contract here'), with well-organized sections throughout.

5 / 5

Total

19

/

20

Passed

Description

58%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 precise and jargon-appropriate for its niche, with a clear statement of what the skill does, but it omits any explicit 'when to use' trigger guidance and lacks the spelled-out 'architecture decision record' phrasing that would broaden natural-term coverage. It is functional but not yet at the standard of the good examples, which all pair capabilities with a 'Use when...' clause.

Suggestions

Add an explicit trigger clause, e.g. 'Use when task context synchronization needs to persist a qualified architecture decision as an ADR', to raise completeness and trigger-term quality.

Spell out 'architecture decision record (ADR)' at least once so users who say the full phrase naturally match the description.

Briefly mention the supersede/correction behavior (a changed decision creates a new dated ADR superseding the prior one) to close the coverage gap in specificity.

DimensionReasoningScore

Specificity

The description names two concrete, well-qualified actions — 'Record one already-qualified decision as an immutable ADR' and 'reusing an equivalent active ADR when present' — which cover this narrow skill's core behavior, but two actions is short of the 'several specific actions' of anchor 4 and other outputs (blocked results, supersede path) are absent.

3 / 5

Completeness

The 'what' is clear (record a decision as an immutable ADR; reuse an equivalent active one), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by 'already-qualified', so completeness is capped at 3 per the judging guideline.

3 / 5

Trigger Term Quality

It includes the natural keyword 'ADR' and 'decision', but misses the spelled-out 'architecture decision record' and common variations like 'decision record' or 'document a decision', matching anchor 3 ('some relevant keywords but missing common variations or synonyms').

3 / 5

Distinctiveness Conflict Risk

'Immutable ADR' and 'equivalent active ADR' establish a clear niche with minimal conflict risk against unrelated skills, though the leading generic term 'decision' carries minor overlap risk with general decision-making assistance, fitting anchor 4 rather than 5.

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

.pi/skills/sce-decision/SKILL.md

Revision

5bf1376

Reviewed

Table of Contents

DiscoveryImplementationValidation

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.

Claim skill