SKILLEMALL.ai
GitHub ↗ RU Sign in

BC compete

Triggers when researching competitive or professional positioning: market intelligence, engineer brands, profiles, and content strategy. Research and strategy only — not code.

simota/agent-skills Agent Skills author: simota 29 files body ≈ 5 782 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Triggers when researching competitive or professional positioning: market intelligence, engineer brands, profiles, and content strategy.

As a process C 59/100 · Has gaps — weak spots: inputs and preconditions, running it twice, progress reporting

ProcedureGitHubMarketingtype 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
B
89/100
safety, quality, tests
Safety 60%
94
Quality 40%
81
Run on models
none yet
Process rating
C
59/100
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

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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Risky intent intent-offensive-security reference/competitive-wargaming.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Purpose: Use this file when Compete must simulate competitor responses, stress-test strategic moves, or run red team / blue team exercises for strategic planning.
  • low Risky intent intent-offensive-security reference/competitive-wargaming.md:10
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Red team / blue team methodology
  • low Risky intent intent-offensive-security reference/competitive-wargaming.md:46
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Red Team** | Compete + domain context | `1-2 sessions` | Deep | Specific competitor response prediction |
  • low Risky intent intent-offensive-security reference/competitive-wargaming.md:141
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## Red Team / Blue Team Methodology
  • low Risky intent intent-offensive-security reference/competitive-wargaming.md:143
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### Red Team (Competitor Perspective)
  • low Risky intent intent-offensive-security SKILL.md:201
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition; documentation table row)
    | `wargame`, `red team`, `blue team`, `competitor response`, `pre-mortem`, `what if we` | Wargame |
    detectortable

Files scanned: 29. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5782 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 59/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 3 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5782 tokens
  • 85Steps. 128 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 175: enough signal without eating the budget
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 128 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (23 of 28)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.