SKILLEMALL.ai
GitHub ↗ RU Sign in

BC helm

Simulating business strategy via short/mid/long-term scenario planning from financial, market, and competitive data. Applies SWOT/PESTLE/Porter, KPI forecasting, roadmaps. Does not write code.

simota/agent-skills Agent Skills author: simota 19 files body ≈ 5 770 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Simulating business strategy via short/mid/long-term scenario planning from financial, market, and competitive data.

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

ProcedureInfrastructureData and analyticsSoftware developmenttype 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
84/100
safety, quality, tests
Safety 60%
94
Quality 40%
69
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. 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/cognitive-biases.md:32
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Red Team / Devil’s Advocate | Build the strongest argument against the preferred path | confirmation bias, groupthink |
  • low Risky intent intent-offensive-security reference/cognitive-biases.md:52
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Strategy design | anchoring, groupthink | run Red Team review |
  • low Risky intent intent-offensive-security reference/cognitive-biases.md:71
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - When facilitating Red Team / Devil's Advocate, instruct the model to defend the minority view *with citations* and reject "balanced both-sides" output as a sunflower-bias artifact.
  • low Risky intent intent-offensive-security reference/scenario-planning-pitfalls.md:61
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - A Red Team or devil’s advocate reviewed the set.
  • low Risky intent intent-offensive-security reference/wargaming-simulation.md:26
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - **CSIS Futures Lab — "It Is Time to Democratize Wargaming Using Generative AI"**: argues GenAI shifts the cost of running wargames from honoraria + travel + facilitator time to data curation, enabli
    detector
  • low Risky intent intent-offensive-security reference/wargaming-simulation.md:36
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Competitor response prediction | **Compete** | Red team / blue team, response probability, behavioral patterns |

Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning body-long SKILL.md body ≈ 5770 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 142): check that old rules are not kept next to new ones — the full check reads the text for contradictions

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. 4 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5770 tokens
  • 100Steps. 120 steps
  • 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 16 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 192: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 120 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (17 of 17)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.