CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

draft-release-notes

Generate categorized release notes draft from scan data. Human must approve before publish.

Quality

64%

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 ./starters/changelog-drafter/.codex/skills/draft-release-notes/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 commendably brief and includes relevant injection-safety guidance for handling untrusted PR data, but the core instruction is under-specified: the template it relies on and the disclaimer it requires are both undefined, leaving the executor to fill in key details. As an instruction-only skill it needs more concrete guidance to be reliably actionable.

Suggestions

Include the actual release notes template inline (or in a referenced file) instead of referring to an unspecified 'standard release notes template'.

Specify the exact review disclaimer text to append to the output, or give a short example of it.

Add the human-approval checkpoint as an explicit step in the body (draft → present for human approval → publish only after approval) so the workflow gate is visible in the procedure, and briefly state how scan-data items map to categories (including items that fit none).

DimensionReasoningScore

Conciseness

The task guidance is lean ("Use the standard release notes template (Features / Fixes / Breaking / Security / etc.)", "Output clean markdown suitable for CHANGELOG or GitHub release. Include review disclaimer.") with no padding or explanation of known concepts. The ~12-line auto-generated "Untrusted input" safety block is relevant (this skill ingests PR titles/bodies) but is generic policy boilerplate rather than skill-specific content, keeping it just short of anchor 5.

4 / 5

Actionability

Concrete category names ("Features / Fixes / Breaking / Security") and a concrete output target ("clean markdown suitable for CHANGELOG or GitHub release") are given, but key details are missing: the "standard release notes template" is referenced but never defined inline or in a file, and the required "review disclaimer" wording is unspecified. This matches anchor 3 (some concrete guidance but incomplete) rather than anchor 4, which requires mostly executable, gap-free guidance.

3 / 5

Workflow Clarity

An implicit sequence exists (categorize scan data → draft → output markdown with disclaimer), but there are no explicit steps or checkpoints in the body; the human-approval gate appears only in the frontmatter description ("Human must approve before publish"), not in the workflow itself. This fits anchor 3 (sequence present but checkpoints missing or implicit), and the single-action exception to score 5 does not apply because the action is not fully unambiguous (undefined template and disclaimer).

3 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/ directories), and the body is under 50 lines, so no external references are needed; the auto-injected block is cleanly delimited with a header. However, "Use the standard release notes template" is a dangling pointer to content that is neither inline nor in any referenced file, which is a minor organization gap — anchor 4 rather than 5.

4 / 5

Total

14

/

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, moderately specific capability with an appropriate safety constraint, but it omits any explicit trigger guidance. Adding a "Use when..." clause with natural trigger terms would resolve its main weaknesses in completeness and trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks for release notes, a changelog draft, or to prepare a GitHub release from scan data."

Include natural synonyms such as "changelog" and "GitHub release" alongside "release notes" so the skill triggers on the phrases users actually say.

Enumerate one or two more concrete actions in the 'what' portion (e.g. "categorize entries into Features / Fixes / Breaking / Security and output clean markdown") to raise specificity.

DimensionReasoningScore

Specificity

"Generate categorized release notes draft from scan data" names the domain and one concrete action (generate a categorized draft), matching anchor 3 (domain plus 1-2 concrete actions, not comprehensive). Not anchor 4 because only a single action is described and the categorization categories, output format, and data handling are not enumerated in the description.

3 / 5

Completeness

The description has a clear 'what' ("Generate categorized release notes draft from scan data") but no 'when' — there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. The 'when' is only weakly implied by the mention of scan data.

3 / 5

Trigger Term Quality

"release notes" is the natural term a user would say, and "draft", "categorize", and "publish" are relevant, but common variations and synonyms are missing ("changelog", "GitHub release", "version", "prepare a release"). This matches anchor 3 (some relevant keywords but missing common variations or synonyms); anchor 4 requires broader keyword coverage that includes those natural phrases.

3 / 5

Distinctiveness Conflict Risk

"release notes draft from scan data" with the constraint "Human must approve before publish" carves a clear niche (draft-only generation from scan data with an approval gate), with only minor overlap risk against closely related skills such as general changelog or commit-message generators. It fits anchor 4 (mostly distinct, minor overlap risk) rather than anchor 5, which expects distinct explicit trigger phrases that this description lacks.

4 / 5

Total

13

/

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

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

cobusgreyling/loop-engineering

Path

starters/changelog-drafter/.codex/skills/draft-release-notes/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.