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.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.archive/helm/SKILL.md

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 well-structured, highly actionable orchestration skill with clear phased workflows and validation/feedback loops. Its main weaknesses are padding from illustrative historical anecdotes and the absence of the referenced reference/ bundle files on disk, which slightly weakens progressive disclosure.

Suggestions

Trim the historical anecdotes in the 'Never' section (Kodak, Blockbuster, HP-Compaq, Yahoo) to one-line rationales; move illustrative case studies into a reference file if retained.

Provide the referenced reference/*.md bundle files (e.g., simulation-patterns.md, financial-modeling-pitfalls.md, cognitive-biases.md) so the one-level-deep references resolve, or inline the small ones and drop the pointers.

Make VERIFY-phase gating explicit (e.g., 'do not proceed to PRESENT until the 3-scenario check and Devil's Advocate challenge pass') to push workflow_clarity toward a 5.

Dimension	Reasoning	Score
Conciseness	Mostly operational and dense, but the 'Never' rules are padded with historical anecdotes Claude does not need ('Kodak's technology blindness and Blockbuster's market misreading', 'the 2002 HP-Compaq merger failed on cultural friction', 'Yahoo's repeated failure'), and BCG citations with full URLs add bulk, placing it at mostly-efficient with some unnecessary explanation.	3 / 5
Actionability	Concrete, executable guidance throughout — explicit SaaS thresholds (churn >1.5x RED, Burn Multiple >2.0x RED, Rule of 40 bands), the SaaS Triangle check, job-statement syntax, named frameworks, and recipe subcommands — with only minor gaps for an instruction-only skill.	4 / 5
Workflow Clarity	Clear sequenced workflows (SCAN->MODEL->SIMULATE->ROADMAP, SURVEY->PLAN->VERIFY->PRESENT) with an explicit VERIFY validation phase and the FORESIGHT TRACK->VALIDATE->CALIBRATE->PROPAGATE feedback loop; not a 5 because some checkpoint gating is implicit rather than enforced.	4 / 5
Progressive Disclosure	A clear Reference Map table signals one-level-deep reference paths and the Recipes table points to 'Read First' files, giving good navigation; however the referenced reference/*.md files are not present in the bundle and substantial dispatch/threshold tables are inlined rather than split out.	4 / 5
	Total	15 / 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.

The description is specific and third-person with solid trigger terms and a clear what-claim, but it omits any explicit 'when to use' guidance, which the rubric caps at completeness 3. It is a strong, mostly-distinct description held back only by the missing trigger clause.

Suggestions

Append an explicit 'Use when ...' clause naming concrete trigger situations (e.g., 'Use when creating strategic roadmaps, forecasting KPIs, or running baseline/optimistic/pessimistic scenario planning').

Add a few natural trigger synonyms users might say (e.g., 'scenario planning', 'strategic roadmap', 'PESTLE analysis', 'Porter's five forces') to broaden trigger-term coverage.

Optionally state a routing contrast (e.g., 'Use Helm for multi-scenario strategy analysis; route pure financial modeling elsewhere') to further sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'short/mid/long-term scenario planning', 'Applies SWOT/PESTLE/Porter, KPI forecasting, roadmaps' — naming the domain with multiple specific capabilities; minor coverage gaps keep it below a 5.	4 / 5
Completeness	Has a clear 'what' but no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Good coverage of natural terms a strategist would say ('business strategy', 'scenario planning', 'KPI forecasting', 'SWOT/PESTLE/Porter', 'roadmaps'), though a few common synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	The 'business strategy via scenario planning' niche plus the explicit 'Does not write code' boundary make it mostly distinct with only minor overlap risk against adjacent analysis skills.	4 / 5
	Total	15 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: simota/agent-skills
Path: .archive/helm/SKILL.md
Commit: f425adc

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.