CtrlK
BlogDocsLog inGet started
Tessl Logo

issue-creation

Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.

69

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A dense, security-conscious instruction skill with fully sequenced steps, pervasive fail-closed validation checkpoints, and an appropriately delegated single reference. Its weaknesses are redundancy across sections, run-on sentences that hurt readability, and unspecified command inputs ($QUERY, $TITLE).

Suggestions

Deduplicate the duplicate-search and label rules that appear in both Hard Rules and Execution Steps, keeping one authoritative statement and one pointer.

Split the long compound sentences in steps 1 and 5 into discrete rules, and add a one-line example of how to build the duplicate-search $QUERY.

DimensionReasoningScore

Conciseness

The body contains no explanations of concepts Claude already knows; every line is non-obvious domain policy with concrete commands. However, duplicate-search and label rules are restated across Hard Rules and steps 4/6/7, and steps 1 and 5 contain very long compound sentences that could be tightened, keeping it at the efficient-with-minor-trimming level.

4 / 5

Actionability

Concrete, executable gh commands are given for label enumeration, duplicate search, candidate capture, create/comment, and read-back, backed by a label expansion contract. Minor gaps remain, such as how to construct $QUERY for the duplicate search and what $TITLE should look like, so it is not fully copy-paste ready.

4 / 5

Workflow Clarity

Nine clearly sequenced steps with explicit validation checkpoints: identity verification against the exact target host, read-back comparison with normalization rules, fail-closed stop conditions, cleanup on every terminal path, and a confirmed | no_write | unknown classification with no blind retries. Validation is thoroughly present for this write-capable workflow, so no cap applies.

5 / 5

Progressive Disclosure

The single bundle reference, references/delegated-workflow-actions.md, exists, is clearly signaled as normative ("read ... completely ... It is normative, not optional background"), and is one level deep with no nested references. The core workflow is inline while delegated post-publication mutation rules live in the reference — content is appropriately split and easy to navigate.

5 / 5

Total

18

/

20

Passed

Description

82%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 concise, third-person description with an explicit trigger clause and concrete grounding ("from repository evidence"). Its main weaknesses are that the what-clause understates the skill's scope and the trigger list misses common phrasings users would naturally use.

Suggestions

Broaden the what-clause to mention commenting and labeling (e.g., "Create, comment on, label, and triage GitHub issues from repository evidence") so the stated capability matches the skill's scope.

Add natural trigger variations such as "open a new issue" or "file a bug" to improve keyword coverage for the phrasings users actually say.

DimensionReasoningScore

Specificity

"Create and triage GitHub issues from repository evidence" names the domain plus two concrete actions, matching the 1-2-concrete-actions anchor. It omits several capabilities the body actually covers (commenting, labeling, workflow mutations), so it is not the several-specific-actions level.

3 / 5

Completeness

The description explicitly answers "what" ("Create and triage GitHub issues from repository evidence") and "when" via the explicit trigger clause ("Trigger: issue creation, bug reports, feature requests, or issue approval"), with concrete trigger phrases. The when-clause is explicit rather than weakly implied, so it exceeds the level-4 anchor.

5 / 5

Trigger Term Quality

"issue creation, bug reports, feature requests, or issue approval" are natural phrases a user would say, but common variations like "open a new issue", "file a bug", or "comment on an issue" are missing, which is the good-coverage-with-gaps level rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

GitHub issue creation and triage is a clear niche with distinct triggers (issue creation, bug reports, issue approval) and minimal overlap risk with unrelated skills.

5 / 5

Total

17

/

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
Gentleman-Programming/gentle-ai
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.