research-foundation-en

Plugin research-foundation-en from marketplace dearcat in DearCaat/research-foundation-skills. Commands read from the repo's manifest — 23 days ago.

Skills (10)

• brainstorming

  Before starting a new research question, analysis, chapter, or idea, expand the candidate hypotheses, research questions, and explanatory angles before judging them.

• debugging

  When there is a bug, error, failed test, regression, performance drop, unexpected result, or anomalous data, establish a tight feedback loop and find the root cause before fixing. Use executing-plans for normal execution without a fault signal.

• delegating

  When assigning, supervising, reusing, restarting, or verifying a sub-agent, choose delegation by context cost, brief it precisely, watch artifacts, and verify what returns.

• executing-plans

  When an agreed plan is ready to implement, execute it faithfully, verify every step, and stop at anything the plan does not cover.

• grilling

  When a research design, analysis, outline, revision strategy, or other trade-off needs user alignment, converge one decision at a time with explicit user approval.

• grounding

  Evidence before opinion: when requirements or context are unclear, or advice is needed, verify primary sources before making a judgment. Do not use it for a normal execution of an already agreed plan.

• handoff

  Explicitly invoked when the user asks to hand the current session to a later session; compress goals, decisions, progress, artifacts, and next steps into a self-contained handoff document.

• red-teaming

  Explicitly invoked only when the user asks to adversarially test a named plan, claim, draft, or decision; attack its premises with evidence and report what breaks or survives.

• truth-seeking

  When the user changes direction, requests a decision, restates a preference, or the agent is about to change its position, separate evidence, correction, preference, and authority before proceeding.

• writing-skills

  When creating, modifying, reviewing, splitting, or merging a skill, maintain its entry point, structure, rule layering, and review discipline. Do not use it to execute the business task described by a neighboring skill.

Hooks (3)

• SessionStart

  cat "${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/principles/foundation.md"

• SubagentStart

  cat "${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/principles/foundation.md"

• SubagentStart

  cat "${PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/principles/foundation-subagent.md"

Similar plugins