{"id":"1979c4a6-e994-403e-85e8-13c5d17c4c4c","shortId":"Fe3spa","kind":"skill","title":"reflect","tagline":">-","description":"# Reflect\n\n## Success Criteria\n\n- Every mistake/friction point cites the specific moment and its impact\n- Improvements are actionable and prioritized (cap defined in step 4)\n- Each skill audit proposes measurable changes (not vague suggestions)\n- User is asked which items to persist to memory\n- If review activity occurred, review-trap patterns are captured to persistent memory, or explicitly marked as \"none\"\n\n## Process\n\n### 1. Session Review\n\nScan the full conversation. For each finding, cite the specific exchange (quote or paraphrase) and its impact.\n\n| Category | Signal |\n|----------|--------|\n| **Mistakes** | Wrong outputs, incorrect assumptions, hallucinated facts |\n| **Friction** | Repeated clarifications, verbose responses, misread intent |\n| **Wasted effort** | Work discarded, wrong approaches tried first |\n| **Wins** | Approaches worth repeating, smooth interactions |\n\nSkip one-time typos, external tool failures, and issues outside agent control.\n\n### 2. Review Activity Scan (if applicable)\n\nIf the session included PR or MR review activity in either direction, run this scan before moving on. Skip only if no reviews happened.\n\n**Inbound (my code was reviewed):** For each review comment received:\n- Did I accept it? If yes, what pattern did the reviewer catch that I missed? Is it a recurring blind spot? Capture the one-liner to persistent memory.\n- Did I push back? If I was right and the reviewer was wrong, nothing to capture. If I was wrong and had to retract mid-thread, capture what I learned.\n\n**Outbound (I reviewed someone else's code):** For each comment I authored:\n- Was it accepted? Nothing to capture -- good call.\n- Was it rejected with a valid counter? That's a review trap. Capture the pattern: what heuristic did I apply that produced a wrong comment?\n\n\"No harvestable items\" is a valid outcome -- say so explicitly. Don't let the step quietly drop off.\n\n### 3. Operational Learnings\n\nBefore listing improvements, scan the session for operational insights worth preserving. Apply the 5-minute filter: would knowing this save 5+ minutes in a future session? If yes, include it. Examples: a project-specific quirk, a command that failed unexpectedly, an approach that worked better than expected.\n\n### 4. Improvements\n\nNumbered list of **concrete improvements**, ranked by impact. Each item: one sentence, imperative, actionable. Cap at 10 items: if more surface, the bottom items are noise -- drop them rather than batching or splitting.\n\nAsk: *\"Which of these should I remember for future chats?\"*\n\nSave approved items to memory files at `~/.claude/projects/<project-slug>/memory/` (replace `<project-slug>` with the slug matching the current working directory, e.g., `-home-ilia-ai-whetstone`) using the Write tool with proper frontmatter (see MEMORY.md index).\n\n### 5. Skill Audit (if skills were used)\n\nFor each skill invoked during the session:\n\n**A. Self-check gate** -- If the skill lacks success criteria + verification loop:\n- Add `## Success Criteria` at top (3-5 measurable checks)\n- Add `## Self-Check` at bottom: \"Verify all success criteria are met before presenting output. If not, iterate (max 5 times).\"\n\n**B. Token efficiency** -- Flag: redundant phrasing, mergeable sections, oversized examples, \"Claude already knows this\" content, inert frontmatter metadata.\n\n**C. Other** -- Missing edge cases, vague directives (rewrite as measurable criteria or remove), naked negations (add \"do Y instead\" or remove).\n\nPresent proposed changes as diffs. Ask: *\"Apply these? (all / pick / skip)\"*\n\n### 6. Capture Markers\n\n**The `remember:` prefix** is the highest-confidence capture signal. When the user writes a message beginning with `remember:`, treat everything after the colon as a memory candidate — no interpretation required. Save directly to the appropriate memory file with a one-line summary and the user's exact phrasing. Example: `remember: we never use Pest, always PHPUnit` → save to `feedback_phpunit_over_pest.md`.\n\n**Correction patterns to watch for** (lower-confidence, batch these for review at `/ia-reflect` time):\n- \"no, use X\" / \"actually, X\" / \"don't use Y, use X\"\n- \"stop doing X\" / \"never X\"\n- \"that's wrong — the right way is...\"\n- repeated clarifications of the same thing within a session\n\n**Optional capture hook**: a `UserPromptSubmit` hook can pattern-match the markers above into `~/.claude/learnings-queue.json` as the user types, so `/ia-reflect` processes the queue deterministically instead of re-scanning the full transcript. Not shipped with this skill; document the convention and leave implementation to users who need it.\n\n### 7. Pattern Detection\n\nIf 2+ similar tasks appear that no existing skill covers, suggest a new skill (1-2 sentence description). Create only after confirmation.\n\n**Proactive trigger:** When the user corrects you, clarifies the same thing twice, or shows frustration, append: \"Tip: Type `/ia-reflect` when you're ready -- I'll review what we can improve.\"\n\n## Self-Check\n\nBefore presenting output, verify all success criteria are met. If any fail, revise (max 5 iterations).","tags":["reflect","skills","iliaal","agent-skills","ai-coding-assistant","ai-tools","claude-code"],"capabilities":["skill","source-iliaal","skill-reflect","topic-agent-skills","topic-ai-coding-assistant","topic-ai-tools","topic-claude-code","topic-skills"],"categories":["ai-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/iliaal/ai-skills/reflect","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add iliaal/ai-skills","source_repo":"https://github.com/iliaal/ai-skills","install_from":"skills.sh"}},"qualityScore":"0.456","qualityRationale":"deterministic score 0.46 from registry signals: · indexed on github topic:agent-skills · 13 github stars · SKILL.md body (5,093 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:07:03.710Z","embedding":null,"createdAt":"2026-05-09T01:05:36.735Z","updatedAt":"2026-05-18T19:07:03.710Z","lastSeenAt":"2026-05-18T19:07:03.710Z","tsv":"'-2':703 '-5':451 '/.claude/learnings-queue.json':650 '/.claude/projects':391 '/ia-reflect':602,656,728 '/memory':392 '1':62,702 '10':357 '2':125,689 '3':288,450 '4':24,339 '5':304,311,418,473,757 '6':525 '7':685 'accept':167,239 'action':17,354 'activ':45,127,139 'actual':607 'add':445,454,508 'agent':123 'ai':406 'alreadi':486 'alway':584 'appear':692 'append':725 'appli':264,302,520 'applic':130 'approach':103,107,333 'appropri':563 'approv':385 'ask':36,374,519 'assumpt':88 'audit':27,420 'author':236 'b':475 'back':197 'batch':371,597 'begin':544 'better':336 'blind':184 'bottom':363,459 'c':493 'call':244 'candid':555 'cap':20,355 'captur':52,186,209,221,242,257,526,536,637 'case':497 'catch':176 'categori':82 'chang':30,516 'chat':383 'check':435,453,457,742 'cite':8,72 'clarif':93,628 'clarifi':717 'claud':485 'code':157,231 'colon':551 'command':328 'comment':163,234,269 'concret':344 'confid':535,596 'confirm':709 'content':489 'control':124 'convent':676 'convers':68 'correct':589,715 'counter':251 'cover':697 'creat':706 'criteria':4,442,447,463,503,749 'current':399 'defin':21 'descript':705 'detect':687 'determinist':660 'diff':518 'direct':142,499,560 'directori':401 'discard':101 'document':674 'drop':286,367 'e.g':402 'edg':496 'effici':477 'effort':99 'either':141 'els':229 'everi':5 'everyth':548 'exact':576 'exampl':321,484,578 'exchang':75 'exist':695 'expect':338 'explicit':57,279 'extern':117 'fact':90 'fail':330,754 'failur':119 'feedback_phpunit_over_pest.md':588 'file':389,565 'filter':306 'find':71 'first':105 'flag':478 'friction':91 'frontmatt':414,491 'frustrat':724 'full':67,667 'futur':315,382 'gate':436 'good':243 'hallucin':89 'happen':154 'harvest':271 'heurist':261 'highest':534 'highest-confid':533 'home':404 'home-ilia-ai-whetston':403 'hook':638,641 'ilia':405 'impact':14,81,348 'imper':353 'implement':679 'improv':15,293,340,345,739 'inbound':155 'includ':134,319 'incorrect':87 'index':417 'inert':490 'insight':299 'instead':511,661 'intent':97 'interact':111 'interpret':557 'invok':428 'issu':121 'item':38,272,350,358,364,386 'iter':471,758 'know':308,487 'lack':440 'learn':224,290 'leav':678 'let':282 'line':570 'liner':190 'list':292,342 'll':734 'loop':444 'lower':595 'lower-confid':594 'mark':58 'marker':527,647 'match':397,645 'max':472,756 'measur':29,452,502 'memori':42,55,193,388,554,564 'memory.md':416 'mergeabl':481 'messag':543 'met':465,751 'metadata':492 'mid':219 'mid-thread':218 'minut':305,312 'misread':96 'miss':179,495 'mistak':84 'mistake/friction':6 'moment':11 'move':147 'mr':137 'nake':506 'need':683 'negat':507 'never':581,618 'new':700 'nois':366 'none':60 'noth':207,240 'number':341 'occur':46 'one':114,189,351,569 'one-lin':188,568 'one-tim':113 'oper':289,298 'option':636 'outbound':225 'outcom':276 'output':86,468,745 'outsid':122 'overs':483 'paraphras':78 'pattern':50,172,259,590,644,686 'pattern-match':643 'persist':40,54,192 'pest':583 'phpunit':585 'phrase':480,577 'pick':523 'point':7 'pr':135 'prefix':530 'present':467,514,744 'preserv':301 'priorit':19 'proactiv':710 'process':61,657 'produc':266 'project':324 'project-specif':323 'proper':413 'propos':28,515 'push':196 'queue':659 'quiet':285 'quirk':326 'quot':76 'rank':346 'rather':369 're':664,731 're-scan':663 'readi':732 'receiv':164 'recur':183 'redund':479 'reflect':1,2 'reject':247 'rememb':380,529,546,579 'remov':505,513 'repeat':92,109,627 'replac':393 'requir':558 'respons':95 'retract':217 'review':44,48,64,126,138,153,159,162,175,204,227,255,600,735 'review-trap':47 'revis':755 'rewrit':500 'right':201,624 'run':143 'save':310,384,559,586 'say':277 'scan':65,128,145,294,665 'section':482 'see':415 'self':434,456,741 'self-check':433,455,740 'sentenc':352,704 'session':63,133,296,316,431,635 'ship':670 'show':723 'signal':83,537 'similar':690 'skill':26,419,422,427,439,673,696,701 'skill-reflect' 'skip':112,149,524 'slug':396 'smooth':110 'someon':228 'source-iliaal' 'specif':10,74,325 'split':373 'spot':185 'step':23,284 'stop':615 'success':3,441,446,462,748 'suggest':33,698 'summari':571 'surfac':361 'task':691 'thing':632,720 'thread':220 'time':115,474,603 'tip':726 'token':476 'tool':118,411 'top':449 'topic-agent-skills' 'topic-ai-coding-assistant' 'topic-ai-tools' 'topic-claude-code' 'topic-skills' 'transcript':668 'trap':49,256 'treat':547 'tri':104 'trigger':711 'twice':721 'type':654,727 'typo':116 'unexpect':331 'use':408,424,582,605,611,613 'user':34,540,574,653,681,714 'userpromptsubmit':640 'vagu':32,498 'valid':250,275 'verbos':94 'verif':443 'verifi':460,746 'wast':98 'watch':592 'way':625 'whetston':407 'win':106 'within':633 'work':100,335,400 'worth':108,300 'would':307 'write':410,541 'wrong':85,102,206,213,268,622 'x':606,608,614,617,619 'y':510,612 'yes':170,318","prices":[{"id":"f5fe1710-6140-40bb-92fd-cd1fffa14268","listingId":"1979c4a6-e994-403e-85e8-13c5d17c4c4c","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"iliaal","category":"ai-skills","install_from":"skills.sh"},"createdAt":"2026-05-09T01:05:36.735Z"}],"sources":[{"listingId":"1979c4a6-e994-403e-85e8-13c5d17c4c4c","source":"github","sourceId":"iliaal/ai-skills/reflect","sourceUrl":"https://github.com/iliaal/ai-skills/tree/master/skills/reflect","isPrimary":false,"firstSeenAt":"2026-05-09T01:05:36.735Z","lastSeenAt":"2026-05-18T19:07:03.710Z"}],"details":{"listingId":"1979c4a6-e994-403e-85e8-13c5d17c4c4c","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"iliaal","slug":"reflect","github":{"repo":"iliaal/ai-skills","stars":13,"topics":["agent-skills","ai-coding-assistant","ai-tools","claude-code","skills"],"license":"mit","html_url":"https://github.com/iliaal/ai-skills","pushed_at":"2026-05-16T13:15:17Z","description":"Curated collection of agent skills for AI coding assistants.","skill_md_sha":"b3325876fd955f199d0c6c2bf9db82731b8893c2","skill_md_path":"skills/reflect/SKILL.md","default_branch":"master","skill_tree_url":"https://github.com/iliaal/ai-skills/tree/master/skills/reflect"},"layout":"multi","source":"github","category":"ai-skills","frontmatter":{"name":"reflect","description":">-"},"skills_sh_url":"https://skills.sh/iliaal/ai-skills/reflect"},"updatedAt":"2026-05-18T19:07:03.710Z"}}