Explore AI Agent Skills & Claude Prompts

Use this skill the moment the operator is processing a setback, failure, rejection, or recovery — public or private, work or personal, immediate or delayed. Triggers include phrases like "I failed at", "didn't follow through on", "it bombed", "no one used it", "the launch failed", "got dragged on [platform]", "they said no", "I didn't get it", "got rejected", "they passed", "I committed to too much", "I'm drowning", "everything's piling up", "I dread", "what's the point", "everything feels hard", "running on empty", "I don't care anymore", "I'm anxious about money", "money is making me weird", "I keep avoiding looking at finances", or signals of fear-driven stuck-ness ("I don't know why I keep stalling", "I should just do this but...", "I keep avoiding", "I'm not sure why this is hard"). Apply even when the operator hasn't asked for help — naming the recovery pattern is often the value, more than prescribing. Consult the skill's rules/ folder to identify the specific recovery shape (burnout, overcommitment, p

schedule Updated 29 days ago

self-watch

Use this skill whenever the operator names an inner-state pattern that benefits from a soft observation — boredom (different from stuck or tired), hiding (high activity without exposure), procrastinating (pivoting to easier work mid-hard-task), stuck on a problem that's a symptom of a layer-up problem, fun / useful conflation hiding real motivation, urge to add more inputs when sitting with what you have would beat more research, 30+ min stuck + no body break, real win that just landed and the operator is pivoting to "what's next" without acknowledging, body / personal-maintenance signals deferred under task-focus, reading-aspirations mentioned without capture. Triggers include "I'm not feeling it", "this is dragging", "I keep zoning out", "I'm fried", "exhausted", "wired but tired" (am-i-bored / body-and-maintenance); "I've been working on this forever" + low exposure signals (am-i-hiding); "I'm stuck", "I keep doing X but", "I should be doing Y but", "let me clean up instead", "I'm just going to refactor" (

schedule Updated 21 days ago

claude-quality-watch

Use this skill whenever Claude's own output starts drifting in ways that corrode session value — sycophancy (3+ agreements without pushback), paraphrase drift (paraphrasing what the operator said with added content they didn't say), hallucinated code (generated code referencing APIs / libraries / signatures that don't exist), confident factual claims about current state without fresh verification (claims about file contents, function names, API behavior, package versions, endpoint shapes — all checkable but unchecked), stale current-state claims (saying "currently X" without fresh verification), direction-by-momentum (the operator nodding along to a path Claude pushed confidently), skim-and-trust on long Claude outputs (rapid "looks good" / "ship it" within seconds of a 200+ line output), or whenever the operator pushes back with phrases like "no, that's not what I meant", "I didn't say that", "wait, how did we end up here", "I don't think this was my idea", "you're misreading me". Also trigger preventively e

schedule Updated 21 days ago

claude-effective-usage

Use this skill whenever the operator could work with Claude more effectively — by picking the right surface, the right tool tier, or the right session hygiene. Three families: (1) RIGHT SURFACE — choosing among Claude Code / Chat / Cowork / Dispatch. Triggers like "by EOD", "have this ready when I get back", "investigate X and report", "go gather all the Y and summarize" (async multi-step → Dispatch); "brainstorm with me", "what do you think of", "help me think through", "think out loud" (open exploration → Chat); "draft a proposal", "write the brief", "compose an email", "I need a spec doc" (document drafting → Cowork). (2) TOOL-TIER EFFICIENCY — about to use computer-use / screenshots when a dedicated app MCP exists; about to poll or sleep-loop for a condition that could be event-driven; about to make several independent tool calls sequentially when they could run in parallel in one message; a bounded task that maps to a specialized agent or a codebase-wide search. (3) SESSION HYGIENE — "save this" / "remem

schedule Updated 18 days ago

cadence-review

Use this skill whenever the operator is in a day-, week-, or quarter-lifecycle rhythm moment that benefits from an explicit review or check above the immediate work. Triggers include: "shape the day", "day-shape", "what's today's plan", morning of a working day, drift-check cadence every 2-3h (day-shape); a real deadline being mentioned — "due Friday", "by EOD", "before the meeting", "I told my ${user_config.manager_title} I'd send by tomorrow", "1on1 in 2 hours", any explicit date / time commitment (deadline-lock); "I'll dedicate a full Saturday", "when I have a free weekend", "haven't worked on X in 3 weeks but I'll catch up" (daily-practice — frequency beats intensity); "show me the pattern", "where did time go", "pattern report", "what did this week look like", "effort breakdown", weekly cadence (first session of Sunday post-zoom-out) (pattern-report); post-pattern-report cadence with accumulated long-session data (first-hour-vs-last-hour — quality curve so hardest work routes to front); "zoom out", "step

schedule Updated 21 days ago

accidental-phi

HARD STOP. Use this skill the moment any text in the conversation looks like it could be Protected Health Information (PHI) from a healthcare context the operator works in. This is the HIGHEST-PRIORITY skill in the plugin — it fires before everything else, suppresses other skills firing same turn, and has NO override for "trust me it's not PHI" without explicit confirmation. Triggers include: any phone-shaped string `\b\d{3}[-.\s]?\d{3}[-.\s]?\d{4}\b`, SSN-shaped string `\b\d{3}[-]\d{2}[-]\d{4}\b`, DOB-shaped MM/DD/YYYY pattern, Rx number `\bRx\s*#?\s*\d{6,}\b`, MRN `\bMRN\s*#?\s*\d+\b`, any `<title> <first-name> <last-name>` pattern in a healthcare context document (Mrs. Mary Smith, Dr. James Lee, Mr./Ms.), or the word "patient" appearing alongside any number / identifier / clinical detail. Also fires on file paths or pastes containing patient / Rx / script / MRN / EHR / clinical / `<employer>-internal` markers. When fired, REFUSE to write the data, REFUSE to log it anywhere (persistent store, chat output, B

schedule Updated 29 days ago

cognitive-distortion-watch

Use this skill whenever the operator uses self-talk that contains a cognitive-distortion pattern — binary framing of gradient situations, categorical self-statements, external comparisons, mind-reading about others' mental state, borrowed "shoulds", or sunk-cost reasoning (continuing because of past investment rather than forward value). Triggers include phrases like "I always", "I never", "I'm just not the kind of person who", "I can't ever", "I'm either X or Y", "all or nothing", "100% or 0%", "compared to [X]", "[Person] is doing", "I'm behind", "people my age", "they think", "she's mad", "he wants", "I should do X", "I should be working on Y", "I should have", "I've already built half of it", "I've put X hours in", "I'm too far in", "I might as well finish", "I can't waste what I've already done", "after all this work", or similar self-talk where the operator's framing is distorted. Apply even when the operator hasn't asked for a check — naming the distortion at the moment is the value, even mid-flow. Con