research — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited research (Agent Skill) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 2 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous research-to-ideation agent. Do NOT ask the user questions. Run the full pipeline below without pausing between phases.
TARGET: $ARGUMENTS
============================================================ PHASE 1: COMPETITIVE GAP ANALYSIS (/compete) ============================================================
PARALLEL EXECUTION: Use the Agent tool to run competitive analysis and feature discovery concurrently when both are independent.
Follow the instructions defined in the /compete skill exactly. Produce the full Competitive Gap Analysis output including all sections (Product Identity, Competitive Landscape, Feature Matrix, Critical Gaps, Strategic Gaps, Differentiators, Our Edges, Industry Trends, Recommended Roadmap, Summary).
Save the report to docs/competitive-gap-analysis.md as specified by the /compete skill (create the docs/ directory if it doesn't exist).
Do NOT stop here. Continue immediately to Phase 2.
============================================================ PHASE 2: TECHNOLOGY TREND RESEARCH ============================================================
Research current technology trends relevant to this project's domain. Use web search to find:
that competitors or adjacent products are adopting (e.g., on-device ML, spatial computing, voice-first UX, AI-native workflows).
or platform capabilities that could unlock new features or reduce cost (e.g., new OS APIs, free-tier expansions, open-source alternatives).
category (e.g., progressive disclosure, ambient computing, micro-animations).
or industry standards that may force or enable product changes.
For each trend, note:
Save to docs/technology-trends.md.
Do NOT stop here. Continue immediately to Phase 3.
============================================================ PHASE 3: USER FEEDBACK ANALYSIS ============================================================
Gather and analyze real user feedback from available sources:
search for reviews. Focus on 1-3 star reviews to surface pain points, and 4-5 star reviews to find beloved features users would miss.
open and recently closed issues for feature requests, common bugs, and recurring complaints.
for discussions about the product category. Note unmet needs users express.
Produce a summary with:
Save to docs/user-feedback-analysis.md.
Do NOT stop here. Continue immediately to Phase 4.
============================================================ PHASE 4: FEATURE IDEATION (/new-features) ============================================================
Now follow the instructions defined in the /new-features skill exactly.
Read ALL .md files in the docs/ directory — this includes:
docs/competitive-gap-analysis.md from Phase 1docs/technology-trends.md from Phase 2docs/user-feedback-analysis.md from Phase 3Extract learnings from every file, synthesize feature ideas, and write the report to docs/NewFeatures-X.md (where X is a 3-word kebab-case theme).
IMPORTANT: Features should heavily draw from ALL prior phases:
============================================================ SELF-HEALING VALIDATION (max 3 iterations) ============================================================
After completing all phases, validate the combined output:
STOP when:
IF STILL FAILING after 3 iterations:
============================================================ OUTPUT ============================================================
When all phases are complete, print a summary:
Files generated:
docs/competitive-gap-analysis.md — Full competitive landscape + gap analysisdocs/technology-trends.md — Technology trends and opportunitiesdocs/user-feedback-analysis.md — User feedback from reviews, issues, and communitydocs/NewFeatures-[X].md — Actionable feature ideas derived from all findingsKey stats:
Next steps:
/spec [feature name] to generate implementation stories/iterate to start building a feature/arch-review to assess architecture readiness for the proposed features============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /research — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
STRICT RULES:
/compete and /new-features apply to their respective phases.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.