CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

circleci

CircleCI integration. Manage Projects, Users, Organizations. Use when the user wants to interact with CircleCI data.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/circleci/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 largely actionable and well-structured, with strong coverage of Membrane connection lifecycle, action discovery, and proxy fallback. Its weaknesses are a token-wasting intro explaining what CircleCI is, an incoherent workflow numbering that references an undefined Step 2, and no validation guidance around destructive actions like Delete Context.

Suggestions

Delete or compress the opening paragraph explaining what CircleCI is — Claude already knows this — and remove the empty Pipeline/Workflow/Job hierarchy with 'Use action names and parameters as needed.'

Fix the workflow numbering: define Step 1/Step 2 explicitly or replace the 'skip to Step 2' and '1b' references with concrete section names.

Add a validation checkpoint before destructive actions (Delete Context, Cancel Workflow), e.g. run get-context or get-workflow first and confirm with the user before running the delete.

DimensionReasoningScore

Conciseness

The opening paragraph ('CircleCI is a continuous integration and continuous delivery (CI/CD) platform. It helps software teams automate...') explains a concept Claude already knows, and the bare Pipeline/Workflow/Job hierarchy followed by 'Use action names and parameters as needed' adds little. Mostly efficient commands and tables, but with some unnecessary explanation — matching anchor 3.

3 / 5

Actionability

Concrete copy-paste commands throughout: install ('npm install -g @membranehq/cli@latest'), auth with headless fallback, connection lifecycle, action search/run with --input JSON, and a proxy flag table. Falls short of 5 because 'membrane action run <actionId>' is never shown with a real action key from the popular-actions table, leaving the common case as a template rather than a worked example.

4 / 5

Workflow Clarity

The connection state-machine guidance (READY / CLIENT_ACTION_REQUIRED with polling and clientAction handling) is strong, but the text twice says 'skip to **Step 2**' without any Step 2 defined, and section '1b' has no numbered 1 or 2. Destructive operations in the actions table (Delete Context, Cancel Workflow) carry no validation guidance, which caps this dimension at 3 per the rubric.

3 / 5

Progressive Disclosure

A single file with no bundle files, organized under clear section headers (Install, Authentication, Connecting, Searching, Popular actions, Running, Proxy, Best practices) and no buried or nested references. The 20-row action table is appropriately inline for discovery. Minor organization gaps (the Step 1/1b/Step 2 numbering inconsistency) keep it below 5.

4 / 5

Total

14

/

20

Passed

Description

66%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 competent description with a proper 'Use when...' clause, third-person voice, and a clearly distinct CircleCI niche. Its main weakness is generic capability language — 'Manage Projects, Users, Organizations' says little about the concrete operations available — and sparse trigger-term coverage beyond the brand name.

Suggestions

Replace 'Manage Projects, Users, Organizations' with concrete operations, e.g. 'Trigger pipelines, rerun workflows, cancel jobs, and manage contexts and environment variables.'

Add natural trigger terms users would say, such as pipelines, builds, CI/CD, workflows, or failed builds, to the 'Use when' clause.

DimensionReasoningScore

Specificity

The description names the domain ('CircleCI integration') and target objects ('Manage Projects, Users, Organizations'), but 'Manage' is a generic verb with no concrete operations like trigger pipelines, rerun workflows, or create environment variables. It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — below 4 because the actions listed are not specific.

3 / 5

Completeness

Both parts are present: 'Manage Projects, Users, Organizations' answers what, and 'Use when the user wants to interact with CircleCI data' is an explicit when-clause, though generic. Fits 'Has both what and when; when could be more explicit or specific' — not 5 since no concrete trigger phrases are given.

4 / 5

Trigger Term Quality

'CircleCI' is the natural keyword and 'interact with CircleCI data' reinforces it, but common variations users would say — pipelines, builds, workflows, CI/CD — are missing. Matches 'Some relevant keywords but missing common variations or synonyms'; not 4 because coverage beyond the brand name is thin.

3 / 5

Distinctiveness Conflict Risk

'CircleCI' appears twice and pins a clear niche with distinct triggers — a user needing this skill would name CircleCI. Minor theoretical overlap with generic CI/CD skills, but the brand-specific trigger keeps conflict risk minimal, matching the top anchor.

5 / 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

membranedev/application-skills

Path

skills/circleci/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.