ReddRadar
Agent skill
opportunity-awareness
Triggers after completing substantive work (finishing a todo, returning from subagent, applying non-obvious convention, receiving user correction). Also: 'what should we capture', 'reusable pattern', 'should this be a skill', 'AGENTS.md update', 'knowledge gap'. Behavioral skill loaded at natural pause points.
Install this agent skill to your Project
npx add-skill https://github.com/axiomantic/spellbook/tree/main/skills/opportunity-awareness
SKILL.md
Opportunity Awareness
Type: Discipline (behavioral nudge)
Invariant Principles
- Pause Points Only - Surface observations after phases complete or at "what's next" moments, never mid-task or during urgent work.
- Specificity Over Volume - One actionable suggestion beats three vague ones; name the exact artifact type and why it matters.
- One-Off Work Stays One-Off - Do not suggest capturing obviously non-reusable tasks; the signal-to-noise ratio of suggestions matters.
After completing substantive work, consider whether what just happened would be valuable as a reusable artifact or project knowledge. Surface observations at natural pause points: after a phase completes, when presenting results, or when the user asks "what's next."
Do not suggest artifacts for obviously one-off tasks. Do not interrupt urgent work.
Artifact Candidates
Mention briefly, offer to draft via background agent:
| Type | Signal |
|---|---|
| Skill | Non-obvious technique or undocumented convention that future sessions need. |
| Command | Multi-step procedure with a clear trigger, identical every time. |
| Agent | Self-contained task with specific tool access and persona, delegatable. |
If the user says yes, dispatch a background agent with the appropriate writing skill (e.g., writing-skills, writing-commands).
Project Knowledge Candidates
Offer to add to AGENTS.md when:
- You searched for build/test/run info that was undocumented
- You made a mistake from an undocumented convention (especially after user correction)
- You discovered a non-obvious dependency or read 5+ files for a one-sentence pattern
- The user explained something not written anywhere
Subagent Observations
Subagents should append a ## Skill Observations section to output when they notice reusable patterns. Check for this section and relay suggestions to the user.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
axiomantic/spellbook
spellbook-auditing
Meta-audit skill for spellbook development. Spawns parallel subagents to factcheck docs, optimize instructions, find token savings, and identify MCP candidates. Produces actionable report.
axiomantic/spellbook
documentation-updates
Use after modifying library skills, library commands, or agents to ensure CHANGELOG, README, and docs are updated
axiomantic/spellbook
project-encyclopedia
[DEPRECATED] Use project-level AGENTS.md files instead. Previously used for first-session codebase onboarding and persistent glossary creation.
axiomantic/spellbook
reviewing-impl-plans
Use when reviewing implementation plans before execution. Triggers: 'is this plan solid', 'review the plan', 'check before I start building', 'anything missing from this plan', 'will this plan work', 'audit the implementation plan'. NOT for: reviewing design documents (use reviewing-design-docs) or creating plans (use writing-plans).
axiomantic/spellbook
session-resume
Session resume protocol and session repairs handling. Loaded when spellbook_session_init returns resume_available: true, or when session_init returns a repairs array. Triggers: 'resume', 'continue', 'where were we', session resume, session repairs.
axiomantic/spellbook
brainstorming
Use when exploring design approaches, generating ideas, or making architectural decisions. Triggers: 'explore options', 'what are the tradeoffs', 'how should I approach', 'let's think through', 'sketch out an approach', 'I need ideas for', 'how would you structure', 'what are my options'. Also invoked by develop when design decisions are needed.
Didn't find tool you were looking for?