CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

codemagic

Codemagic integration. Manage data, records, and automate workflows. Use when the user wants to interact with Codemagic data.

Quality

61%

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/codemagic/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 strong, executable CLI reference: concrete commands for install, auth, connection lifecycle with state branching, action search/run, and a proxy escape hatch, with a sensible workflow order. Its weaknesses are the concept-explaining intro and marketing-ish phrasing that pad the token budget, plus the incoherent step numbering (a dangling "Step 2" and an orphan "1b") and the cryptic overview tree. Fixing the numbering and trimming the intro would lift the two lowest dimensions.

Suggestions

Delete or compress the opening paragraph explaining what Codemagic is and who uses it — Claude already knows this — and trim promotional phrasing ("burn less tokens", "focus on the integration logic rather than auth plumbing").

Fix the workflow numbering: the text says "skip to Step 2" and has a section "1b" but no numbered steps exist; either number the steps (1. Install, 2. Authenticate, 3. Connect, 4. Search, 5. Run) or remove the dangling references.

Replace the vague "Codemagic Overview" hierarchy tree and "Use action names and parameters as needed" line with either a one-sentence data-model orientation or move the action catalog into a references file.

DimensionReasoningScore

Conciseness

The intro paragraph ("Codemagic is a CI/CD platform specifically designed for mobile app development. It helps mobile developers automate the building, testing, and deployment...") explains a concept Claude already knows, and lines like "This will burn less tokens and make communication more secure" and "so you can focus on the integration logic rather than auth plumbing" are padding. The bulk of the body is efficient command documentation, so this lands on 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than 2, which requires several padded sections.

3 / 5

Actionability

Concrete, copy-paste-ready commands throughout: `npm install -g @membranehq/cli@latest`, `membrane connection ensure "https://codemagic.io/start/" --json`, `membrane action run <actionId> --connectionId=... --input '{"key": "value"}' --json`, plus an action key table and proxy flag table. Minor gaps keep it below 5: `membrane login --tenant` shows no value syntax for the tenant flag, and the doc inconsistently invokes `membrane` vs `npx @membranehq/cli`.

4 / 5

Workflow Clarity

The sequence (install → authenticate → connection ensure → poll for READY → handle clientAction states → search actions → run → proxy fallback) is clear, with explicit state-based checkpoints (READY / CLIENT_ACTION_REQUIRED / CONFIGURATION_ERROR), an error field to check, and a re-poll loop after user action. It is not 5 because the text says "skip to Step 2" and labels a section "1b" while no numbered steps or Step 2 heading exist — the numbering is incoherent — and build/destructive actions like Cancel Build and Delete All Application Caches get no verification guidance.

4 / 5

Progressive Disclosure

No bundle files exist, but the ~150-line body is well organized with clear section headers, tables, and code blocks in logical order, and nothing is buried. It is not 5 because content that could live in reference files (the popular-actions catalog, proxy flag table) is fully inlined and the "Codemagic Overview" hierarchy tree followed by "Use action names and parameters as needed" is cryptic filler that adds organization noise.

4 / 5

Total

15

/

20

Passed

Description

37%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 leans almost entirely on the product name for both specificity and distinctiveness while its action and trigger language is generic boilerplate. It technically includes a 'Use when' clause, but neither the capabilities nor the trigger terms would help a model understand when or why to use it. Rewriting around concrete Codemagic capabilities (builds, deployments, applications, artifacts) would fix most dimensions at once.

Suggestions

Replace "Manage data, records, and automate workflows" with concrete capabilities, e.g. "Start and cancel builds, list and manage applications, and manage build artifacts and caches in Codemagic CI/CD."

Add natural trigger terms users would actually say: builds, CI/CD, deploy, release pipeline, mobile app, Flutter, iOS, Android — e.g. "Use when the user mentions Codemagic, wants to start or monitor mobile builds, or manage their mobile CI/CD pipeline."

Drop the vague "interact with Codemagic data" phrasing in the trigger clause; tie the 'when' to the concrete tasks listed in the 'what' so the two halves reinforce each other.

DimensionReasoningScore

Specificity

The description names the domain ("Codemagic integration") but the actions are entirely generic — "Manage data, records, and automate workflows" describes no concrete capability (no builds, deployments, applications, or artifacts), matching the anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no specific concrete action is ever named, and not a 1 because the domain is at least identified.

2 / 5

Completeness

Both a 'what' ("Manage data, records, and automate workflows") and a 'when' ("Use when the user wants to interact with Codemagic data") are present, but the 'what' is vague about what the skill actually does (build/deploy management, not generic data management). It sits between anchor 2 (vague what, no when) and anchor 4 (both present, when could be more specific) — the explicit 'Use when' clause is present but the 'what' half is too vague to score 4.

3 / 5

Trigger Term Quality

The only real keyword is the proper noun "Codemagic"; natural phrases a user would actually say — builds, CI/CD, deploy, release, Flutter, iOS, Android, mobile app — are all missing, and "interact with Codemagic data" is not phrasing a user would naturally use. This matches 'One or two generic keywords; missing the natural phrases users say' rather than 3, which requires a broader set of relevant keywords.

2 / 5

Distinctiveness Conflict Risk

The proper noun "Codemagic" gives it a distinct trigger, but "Manage data, records, and automate workflows" is boilerplate shared by virtually every integration skill of this family, so it 'could still overlap with similar skills'. Not 4 because beyond the product name the description offers no distinctive capability or trigger to separate it from sibling integration skills.

3 / 5

Total

10

/

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/codemagic/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.