CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

fix-ci

Fix the failed CI checks for the current session. Use when the user requests a CI fix via the Fix Checks button in the Changes toolbar.

Quality

76%

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 ./src/vs/sessions/skills/fix-ci/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a tight, well-structured instruction-only skill: it tells the agent exactly what information to use, how to diagnose failures, and to validate locally before finishing. Remaining gaps are minor — a redundant opening paragraph, no fetch-commands fallback, and no explicit retry loop when validation fails.

Suggestions

Remove or merge the introductory paragraph with the Workflow section to eliminate the restatement of steps 1-3.

Add an explicit feedback loop after the validation step, e.g. "If validation still fails, re-examine the check output and iterate."

Include a concrete fallback command for pulling more check detail, such as `gh pr checks <number> --json` or `gh run view <run-id> --log-failed`.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence, with no padding explaining what CI is. It sits at anchor 4 rather than 5 because the opening paragraph ("Use the failed check information provided with this message... to identify the root causes and make the necessary code changes") largely restates workflow steps 1-3 and could be trimmed.

4 / 5

Actionability

The guidance is concrete and directed: it specifies what the attached check information contains, gives root-cause examples ("compile errors, lint/hygiene violations, failing tests"), and concrete validation examples ("compile, lint, run the relevant tests"). It falls short of anchor 5 because no commands are given for fetching details when the attached information is insufficient (e.g. `gh pr checks` or `gh run view`).

4 / 5

Workflow Clarity

A clear 4-step sequence (read info, identify root cause, make changes, validate locally) with an explicit validation checkpoint in step 4. It does not reach anchor 5 because there is no explicit feedback loop for what to do when local validation still fails (fix and re-validate). This is not a destructive or batch operation, so the workflow-clarity cap does not apply.

4 / 5

Progressive Disclosure

This is a simple skill under 50 lines with no need for external references, and the body is well organized into a directive statement plus a numbered Workflow section. Per the rubric's simple-skill note, this earns a 5 with well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

62%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 clearly answers both what and when with a distinct, well-targeted trigger tied to the Fix Checks button. Its main weaknesses are limited action specificity and sparse natural trigger-term coverage beyond the exact button path.

Suggestions

Enumerate the concrete actions involved, e.g. "Fix failed CI checks by reading check annotations and output, diagnosing root causes like compile errors, lint violations, or failing tests, and making the code changes to make checks pass."

Broaden trigger terms beyond the button path to include natural phrasings users would say, such as "failing checks", "build failure", "CI is red", or "fix the tests".

Consider mentioning the outcome (getting the PR checks green) to sharpen both the what and the distinctiveness of the trigger.

DimensionReasoningScore

Specificity

"Fix the failed CI checks for the current session" names the domain and a single concrete action, matching the '1-2 concrete actions, not comprehensive' anchor. It is below anchor 4 because only one action is stated with no enumeration of what fixing involves.

3 / 5

Completeness

Both what ("Fix the failed CI checks for the current session") and when ("Use when the user requests a CI fix via the Fix Checks button in the Changes toolbar") are present and explicit. It falls short of anchor 5 because the when-clause covers only a single narrow trigger path rather than a broader set of concrete trigger phrases.

4 / 5

Trigger Term Quality

"CI fix" and "failed CI checks" are natural terms users would say, but common variations like "failing tests", "build failure", or "red pipeline" are missing. This fits the 'some relevant keywords but missing common variations or synonyms' anchor rather than anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The CI-fixing niche with a button-specific trigger is mostly distinct with minimal conflict risk, matching anchor 4. It does not reach anchor 5 because "fix failed CI checks" could still mildly overlap with general debugging or test-fixing skills.

4 / 5

Total

14

/

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

posit-dev/positron

Path

src/vs/sessions/skills/fix-ci/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.