SKILLEMALL.ai
GitHub ↗ RU Sign in

DC Linear

Managing Linear issues, projects, and teams. Use when working with Linear tasks, creating issues, updating status, querying projects, or managing team workflows.

The skillemall take

The skill promises Linear task management: creating issues, updating statuses, querying projects, and team coordination. In practice — a folder with 61 files and 41 scripts that were never run on models or tested in sandbox.

Scores indicate middling quality: code quality 66%, process 61%, safety 82%. Checks found 10 medium and low-severity issues, nothing critical. Compatible across many platforms from Claude to DeepSeek. Without actual model runs and isolated environment tests, it remains unclear whether it works at all or interacts correctly with Linear's API.

You can install it as an experiment, but be ready to debug.

wrsmith108/linear-claude-skill Agent Skills author: wrsmith108 61 files · 41 scripts body ≈ 5 697 tokens Open the sourcegithub.com↗ analyzed 10 h ago

Managing Linear issues, projects, and teams.

As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureLinearAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
D
76/100
safety, quality, tests
Safety 60%
82
Quality 40%
66
Run on models
none yet
Process rating
C
61/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 10

✓ No critical or high findings

Medium and low: 10
  • medium Dangerous commands cmd-shell-rc README.md:48
    Writes to a shell startup file
    echo 'export LINEAR_API_KEY="lin_api_your_key_here"' >> ~/.zshrc
  • medium Broad scope meta-broad-allowed-tools SKILL.md:1
    Broad tool permissions pre-approved: Bash
    allowed-tools: mcp__linear WebFetch(domain:linear.app) Bash
  • low Secrets in code secret-high-entropy-token package-lock.json:85
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…aEn+m3Pf…w8j/8LBJ…VNJ+Q==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:110
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…nS4+204nGb1RiX/WXYH…II9/e2DW…VvQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:172
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…cAz+ivBu…Lvw==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:257
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…IxX/wd5n…MGF+pv6g…i2Z+Wnj9/KjGz…4Eg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:291
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…BQM/qZ3R+9TEU…es4+qu1b…BFA==",
    detector
  • low Dangerous commands cmd-shell-rc scripts/query.ts:43
    Writes to a shell startup file (string literal in code, not executed)
    console.error('     echo \'export LINEAR_API_KEY="lin_api_..."\' >> ~/.zshrc\n');
    code literal
  • low Exfiltration read-dotenv SKILL.md:70
    Reads a .env file
    cat .env.schema | grep LINEAR
  • low Exfiltration read-dotenv SKILL.md:80
    Reads a .env file
    cat .env

Files scanned: 59. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning body-long SKILL.md body ≈ 5697 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 438): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 61/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 21 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 40Consistency. Frontmatter name (Linear) differs from the folder (linear-claude-skill)
  • 50When it triggers. No condition that starts the skill
  • 70Execution cost. Instruction body is 5697 tokens
  • 85Steps. 66 steps, 3 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Failures and branches. 5 branches, has a failure section
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • -315 of 17 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 161: enough signal without eating the budget
  • +4Structure: 45 headings
  • +3Step-by-step instructions: 66 items
  • +4Has examples (38 code blocks)
  • +4Reference files are cited in the instructions (2 of 2)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.