CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

decider

Load to create, search, or supersede an architecture decision record.

Quality

76%

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/decider/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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 exceptionally lean and its CLI claims fully verify against the shipped script, but the bundle ships none of the five referenced workflow/schema/template files, leaving the create/update path unexecutable, and the `check` validation action is never woven into a workflow for the skill's destructive INDEX/record edits.

Suggestions

Ship the referenced bundle files — workflows/create-decision.md, workflows/update-decision.md, schemas/decision-format.md, templates/decision-entry.md, templates/index-row.md — or inline their essential steps; all five resolve to no file in the bundle, so the primary create/update procedure is unreachable.

Weave `decisions check` into the create/update path as an explicit validation checkpoint (e.g., 'after any INDEX edit, run decisions check and fix error= findings before proceeding'); the action exists in the CLI but the body never says when to run it, and the skill includes destructive record removal.

Add a short numbered creation sequence in the body (next-id → draft from the template → add the INDEX row → decisions check) so the core workflow is executable even without the workflow files.

DimensionReasoningScore

Conciseness

The 44-line body has zero padding: no tutorial-level explanation of what an ADR is, no library talk, and every sentence states a rule, criterion, or pointer ("A record exists to stop a reversal", the warranted/not-warranted lists, the approval phrasing). Not 4: there is no over-explanation left to trim, matching the 'every token earns its place' anchor.

5 / 5

Actionability

The CLI block's claims all verify against the shipped script (actions `search`, `search --issue`, `list`, `next-id`, `get`, `check`; `DECISIONS_DIR`/`DECISIONS_BASE_REF`/`DECISION_ID_*`; "There is no bare `issue` action" confirmed) and the approval phrasing is copy-paste ready. But the core create/update procedures are delegated to files absent from the bundle ("Follow `workflows/update-decision.md`", "Format: `schemas/decision-format.md`", "`templates/decision-entry.md`"). Anchor 3 fits: concrete guidance exists but the primary action's procedure is unreachable — more than a minor gap.

3 / 5

Workflow Clarity

The trigger→workflow table and the explicit approval checkpoint ("Never create a decision document without explicit user approval") structure the flow, but the actual step sequences live in the missing workflow files and the CLI's `check` action is never placed in a workflow. Because the skill involves destructive operations (removing a routine record's document, INDEX edits), the missing validation steps cap this at 3 per the destructive/batch guideline.

3 / 5

Progressive Disclosure

The body is a well-sectioned, one-level-deep hub (workflows table, format pointers, `decisions --help` delegation), but scored against the actual bundle only `scripts/decisions` exists: `workflows/create-decision.md`, `workflows/update-decision.md`, `schemas/decision-format.md`, `templates/decision-entry.md`, and `templates/index-row.md` are all absent, so most navigation targets dangle. Better organized than anchor 2, but five broken reference paths are not anchor 4's 'minor organization gaps'.

3 / 5

Total

14

/

20

Passed

Description

78%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 compact, specific, and explicit about both what it does and when to load it, with a clear ADR niche and minimal conflict risk. Its only gaps are missing common synonyms (notably "ADR") and slightly narrower capability coverage than the skill actually provides.

DimensionReasoningScore

Specificity

"create, search, or supersede an architecture decision record" lists three concrete actions in a specific domain, matching anchor 4. Not 5: coverage has gaps — the skill also handles withdrawal/retirement/removal, supersession tracking, and INDEX maintenance, none of which appear.

4 / 5

Completeness

"Load to create, search, or supersede an architecture decision record" answers both what (those three actions on decision records) and when (load it when you need to do them) — an explicit trigger equivalent to a 'Use when' clause, so not capped at 3. Not 5: it lacks the concrete, separate trigger phrases of anchor 5's example (e.g., 'when the user mentions ADRs or decision records').

4 / 5

Trigger Term Quality

"architecture decision record", "create", "search", "supersede" are terms a user would naturally say when needing this skill. Not 5: common synonyms and abbreviations are missing — "ADR", "decision log", "document a decision" — which anchor 5's example includes.

4 / 5

Distinctiveness Conflict Risk

"architecture decision record" names a precise, well-known artifact niche with distinct trigger verbs (create, search, supersede); no other skill category would plausibly collide with these triggers. Anchor 5's 'clear niche with distinct triggers; minimal conflict risk' fits exactly.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

vanillagreencom/kendex

Path

skills/decider/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.