CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kanban

Tracks coding work on a file-based kanban board: turns requests into cards with testable acceptance criteria and records verification evidence. Use for kanban board requests.

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

This is a strong, command-reference-style skill body: every instruction is executable, workflows are sequenced with real validation gates and error-recovery loops, and it trusts the reader's competence throughout. The only notable imperfections are minor redundancy around the gate rules and exit-code semantics, and a command table that pushes the file toward reference-file length.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes Claude's competence — it never explains what kanban, git, or worktrees are, and every line instructs. Minor repetition keeps it from anchor 5: the no-gate-workaround rule and exit-3 behavior are each explained twice (Hard rules vs. Review to Done; Review to Done vs. Failure handling), and paragraphs like the standup-reconstruction and readiness-check passages could be tightened.

4 / 5

Actionability

Guidance is fully executable: a command table gives exact forms with complete flag syntax (e.g. `new --title "<title>" [--priority P0-P3] ...`), the approve/done gate commands are copy-paste ready in a code block, and failure handling maps exact exit codes (1/2/3) to exact responses. Concrete examples cover the common cases.

5 / 5

Workflow Clarity

Intake, execution loop, and review-to-done are each clearly numbered with explicit validation checkpoints (`check add`/`check set` with observed evidence, `validate`, `doctor`) and genuine feedback loops — "If a check fails, fix the cause, re-run it, and `check set` the new result", and the exit-1-before-exit-3 readiness check for gated commands. Error recovery is explicit throughout.

5 / 5

Progressive Disclosure

No bundle files exist; the single body is well-sectioned and defers full usage to the CLI itself ("`--help` prints the whole usage block"), which is appropriate one-level-deep disclosure. It sits above anchor 3 because structure and placement are good, but below anchor 5 because at ~150 lines the exhaustive command table borders on reference material that could live in a separate file.

4 / 5

Total

18

/

20

Passed

Description

67%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 specific, concrete, and clearly anchored in a distinct kanban-tracking niche, with an explicit what and a present but narrow when-clause. Its main weakness is trigger coverage: "Use for kanban board requests" captures only one phrasing, even though the frontmatter's separate whenToUse field lists richer triggers ("asks what to work on next", "wants work tracked as cards") that the description itself does not carry.

Suggestions

Broaden the 'Use for' clause with natural trigger variations, e.g. 'Use for kanban board or task board requests, when the user asks what to work on next, or wants coding work tracked as cards.'

Mention one or two more distinguishing capabilities (e.g., linking commits/PRs to cards, human approval gates) so the 'what' covers more of the skill's scope without adding fluff.

Mirror the strongest natural phrases from the whenToUse field into the description itself, since the description is what users and skill-selection see first.

DimensionReasoningScore

Specificity

"turns requests into cards with testable acceptance criteria" and "records verification evidence" are several concrete, specific actions in a named domain ("file-based kanban board"), though capabilities like linking commits, review gates, and standup go unmentioned. It exceeds the 1–2 concrete actions of anchor 3 but the coverage gaps keep it from anchor 5.

4 / 5

Completeness

It answers "what" clearly (tracks coding work, turns requests into cards, records verification evidence) and includes an explicit "Use for kanban board requests" when-clause. The when is present but narrow and could be more specific with varied trigger phrases, matching anchor 4 rather than anchor 5.

4 / 5

Trigger Term Quality

The natural user-facing terms are essentially "kanban board" and "cards", and the trigger clause "Use for kanban board requests" is a single narrow phrase. Common variations a user would actually say — "task board", "track tasks", "what should I work on next" — are missing, which is more than the "a few missing" of anchor 4.

3 / 5

Distinctiveness Conflict Risk

"file-based kanban board" with "cards with testable acceptance criteria" and "verification evidence" carves a clear, distinct niche with a specific trigger. There is minor overlap risk with generic task/todo-tracking and planning skills because "coding work" is broad, keeping it below anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

pmcf69/ss-demo-ungated

Path

.dsh/skills/kanban/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.