CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

decider

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

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/decider/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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.

An exceptionally lean, high-signal body that assumes Claude's intelligence and gives concrete, verifiable commands and rules. Its main weaknesses are structural: the multi-step workflows and validation checkpoints are delegated to files missing from the bundle, and most referenced paths (workflows, schemas, templates) do not resolve.

Suggestions

Ship the referenced `workflows/`, `schemas/decision-format.md`, and `templates/` files in the bundle (or inline a minimal record/INDEX-row template) so the body's references resolve.

Wire `decisions check` explicitly into the update workflow as a validation checkpoint (e.g. "after any INDEX edit, run `decisions check`; fix duplicates before proceeding") to create a validate-fix-retry loop.

Add one short worked example of invoking the CLI (e.g. `decisions search --issue PROJ-189`, `decisions next-id`) inline instead of deferring everything to `--help`.

DimensionReasoningScore

Conciseness

The body is ~40 dense lines covering warrant criteria, binding rules, lifecycle semantics, and an approval gate with zero padding and no explanation of concepts Claude already knows — e.g. "A record exists to stop a reversal: a reviewer or a future agent, reading the code alone, would undo the choice because the code cannot show its reason." Every line instructs; it fully assumes competence.

5 / 5

Actionability

Concrete and verifiable: the CLI block (".agents/skills/decider/scripts/decisions <command> [options]"), named actions, env vars, and exact copy-paste approval phrasing ("Want me to create a decision entry?") all check out against the bundled script. It falls short of 5 because the invocation shown is a placeholder template — specific command examples (e.g. `decisions search --issue PROJ-189`) live only behind `--help`, and the format/creation specifics defer to files not shown.

4 / 5

Workflow Clarity

Triggers, binding rules, and the approval gate are clearly stated, and the workflow table maps each trigger to a file, but the actual step sequences and validation checkpoints are delegated to `workflows/create-decision.md` and `workflows/update-decision.md`, which are not present in the bundle. The `check` action exists in the CLI but is never explicitly wired in as a validation checkpoint after INDEX edits, so checkpoints remain implicit — matching anchor 3 rather than 4.

3 / 5

Progressive Disclosure

The body is well-sectioned with one-level-deep, clearly signaled references, and pushing CLI detail to `decisions --help` is good practice. But scoring against the actual bundle: of the six referenced paths, only the `scripts/decisions` script 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 navigation from the body breaks for five of them.

3 / 5

Total

15

/

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.

A terse, domain-specific description with a clear "what", but no explicit "when to use" trigger clause and no synonyms ("ADR", "decision log") that users naturally say. The niche is distinct, so conflict risk is low, but discoverability from natural queries is weakened.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions ADRs, architecture decision records, decision logs, or asks to record/supersede a design decision."

Include the common synonyms "ADR" and "decision log" so natural user phrasings match the description.

Mention INDEX maintenance and record removal/retirement to close the coverage gap between the description and the skill's actual workflows.

DimensionReasoningScore

Specificity

"Load to create, search, or supersede an architecture decision record" lists several distinct concrete actions tied to a named domain. It sits below 5 because coverage has real gaps — the skill also handles INDEX maintenance, record removal, and retirement, none of which appear — and above 3 because more than 1-2 specific actions are given.

4 / 5

Completeness

The "what" is clear (create, search, supersede decision records), but there is no "Use when..." clause or equivalent trigger guidance anywhere — "Load to" states when to load the skill only in the most implicit way. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3; it is not 2 because the "what" half is fully present.

3 / 5

Trigger Term Quality

"architecture decision record" is the natural noun phrase, and "create", "search", "supersede" are terms users would say, but the most common variation practitioners actually type — "ADR" — plus "decision log" are missing. Not 4 because the absent "ADR" shorthand is the single most common synonym for this domain.

3 / 5

Distinctiveness Conflict Risk

"architecture decision record" plus the specialized verb "supersede" carves a clear niche unlikely to fire for unrelated skills. It is not 5 because there is minor overlap risk with general documentation, notes, or planning skills (the body itself references a docs-writing skill), and the absence of explicit triggers leaves disambiguation to the noun phrase alone.

4 / 5

Total

14

/

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.