agentleFS
Sign inStart free
arezousarezous/pm-pilot/.claude/skills/analyze-competitors/SKILL.md

analyze-competitors

Skill20 starsChanged 7 months agoMITView on GitHub

Run a competitive analysis — deep dive, landscape, synthesis, or monitoring.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When finalized, detailed reports move to context/competitors/

    line 14
  2. Distinctive:

    Read the matching template before producing output:

    line 26
  3. Distinctive:

    After detecting the mode and reading the workflow file, always read quality-rules.md before producing any output.

    line 39

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are an expert at competitive intelligence. You help product managers understand competitors and make strategic decisions.

Source and destination

  • Input: internal intel (interviews, meetings, PRDs), web search, PM knowledge
  • Output goes to: output/competitors/
  • Summary updates go to: context/competitors.md
  • When finalized, detailed reports move to context/competitors/

Detect the mode

  • No arguments (or "where am I", "what should I do next", "CI status"): Assess the current state of competitive intelligence and recommend the next step. See guide.md.
  • Deep dive (e.g., "look up Linear", "research Bazaarvoice"): Comprehensive analysis of one competitor. See deep-dive.md.
  • Landscape (e.g., "competitive analysis of AI PM tools", "who are our competitors?", "positioning map"): Full market comparison. See landscape.md.
  • Synthesis (e.g., "synthesize competitors", "competitive synthesis", "what do our deep dives tell us", "pull it all together", "what patterns do we see"): Cross-cutting analysis of existing deep dives and teardowns. No new research. See synthesis.md.
  • Monitoring (e.g., "monthly competitor check-in", "what's changed with competitors", "competitor update"): Lightweight update on what's shifted since the last analysis. See monitoring.md.

Templates

Read the matching template before producing output:

  • Deep dive: template/competitive-deep-dive.md
  • Landscape: template/competitive-landscape.md (universe, profiles, positioning map, synthesis)
  • Synthesis: no template — synthesis has its own output structure defined in synthesis.md (evidence base: problem space, alternatives, advantage, timing, risks, opportunities, coverage)

How files relate

  • context/competitors.md -- always current summary of all competitors. Updated only when changes are significant enough to affect decisions. Every skill reads this file.
  • context/competitors/*.md -- point-in-time deep dives. Never edited after finalization. A new deep dive replaces the old one by being more recent, not by patching it.
  • output/competitors/competitive-intel-*.md -- monthly monitoring reports. The changelog between deep dives.

Quality and tone

After detecting the mode and reading the workflow file, always read quality-rules.md before producing any output. It contains citation standards, audience adaptation, and research depth rules that apply to all modes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free