skillify
This skill should be used when the user says "skillify", "extract a skill", "learn this", "distill this into a skill", "turn this into a skill", "capture this workflow", "save this pattern", "this should be a skill", "can we reuse this?", or wants to capture a reusable pattern from the current session and turn it into a new skill. It scans the conversation for workflow, code, and decision patterns, then hands off to skill-development for actual creation.
What this skill does
# Skillify Extract reusable patterns from the current conversation session and delegate their creation as skills to `plugin-dev:skill-development`. This skill extracts and shapes -- it never creates skills directly. ## When to Use **Explicit triggers:** - User says "skillify", "extract a skill", "learn this", "distill this into a skill" - User says "turn this into a skill", "capture this workflow", "save this pattern" - User asks "can we reuse this?" or "this should be a skill" **Proactive triggers (suggest briefly):** - After completing a multi-step debugging workflow that solved a non-trivial problem - After a deployment procedure that required specific sequencing or gotchas - After discovering a decision tree that recurred across sessions - When a conversation reveals a repeatable process worth codifying - Briefly suggest: "This looks like a reusable pattern. Want me to skillify it?" ## Core Flow ### Phase 1 -- Extraction Engine Scan the full session context for extractable patterns. Prioritize in this order: 1. **Workflow patterns** (PRIMARY) -- Multi-step processes, decision trees, sequences that solved problems, debugging workflows, deployment procedures, investigation playbooks. 2. **Code patterns** (SECONDARY) -- Reusable approaches, conventions, architectural patterns that emerged organically during implementation. 3. **Decision patterns** (SECONDARY) -- Recurring choices, rules of thumb, heuristics that guided the session's direction. For each pattern found, construct a **pattern brief**: ``` Pattern Name: <descriptive name> Type: workflow | code | decision Summary: <1-2 sentence description> Steps/Rules: <the actual pattern, numbered if workflow> When to use: <trigger conditions> Why it works: <session context for why this approach was chosen> ``` **If no patterns found:** Exit gracefully. Do not force extraction. Instead, suggest alternatives based on what WAS observed in the session: - A memory entry (if the insight is session-specific context) - A CLAUDE.md rule (if it's a standing instruction) - A feedback entry (if it's a behavioral correction) State clearly: "No reusable patterns found in this session. Here's what I did find and where it fits better: ..." **If session is too short:** Say so honestly. "This session doesn't have enough context to extract meaningful patterns. Continue working and invoke skillify again later." ### Checkpoint 1 -- Pattern Approval Present all discovered patterns as a numbered list of pattern briefs. Then STOP and wait for user input. ``` I found N extractable pattern(s): 1. **<Pattern Name>** (workflow) <Summary> 2. **<Pattern Name>** (code) <Summary> Which patterns should I hand off to skill-development? - Pick by number (e.g., "1 and 3") - Refine a brief (e.g., "update 2 to include X") - Reject all (e.g., "none of these") ``` Do NOT proceed until the user explicitly approves, refines, or picks patterns. If the user rejects all, exit gracefully. After approval, ask: **"Which plugin should this skill live in?"** Wait for the answer before proceeding. ### Phase 2 -- Handoff to skill-development For each approved pattern, invoke `plugin-dev:skill-development` via the Skill tool with a structured handoff prompt containing: 1. The approved pattern brief -- verbatim, as approved or refined by the user. 2. The target plugin path -- as specified by the user. 3. The directive: > "The user has already completed the discovery phase. Use the pattern brief below as your input -- skip steps 1-2 of your workflow and proceed directly to creating the skill structure and writing the SKILL.md." Construct the handoff as a single, self-contained prompt. Do not assume skill-development has access to this conversation's context. ### Phase 3 -- Quality Gate After `plugin-dev:skill-development` completes, invoke `plugin-dev:skill-reviewer` to validate the newly created skill. Surface the quality report to the user. ### Checkpoint 2 -- Validation Present the skill-reviewer's quality report. STOP and wait for the user to review. - If the user accepts: confirm completion. - If the user requests changes: relay feedback to skill-development for another pass. - If skill-development or skill-reviewer fails at any point: surface the error clearly. Do NOT attempt to create the skill directly. ## Edge Cases | Scenario | Response | |----------|----------| | No patterns found | Exit gracefully, suggest memory entry / CLAUDE.md rule / feedback instead | | Session too short | Say so honestly, suggest invoking later | | Multiple patterns found | Numbered list, user picks which to extract | | User wants all patterns | Process sequentially, one skill-development handoff per pattern | | skill-development fails | Surface the error, do not create the skill directly | | skill-reviewer fails | Surface the error, still present the skill for manual review | | Pattern is too vague | Ask user to refine the brief before handoff | | User provides input instead of session scan | Politely redirect: "Let me scan the session first, then we can refine" | ## This Skill Does NOT - Write SKILL.md files directly -- that is skill-development's job. - Create directory structures for new skills -- that is skill-development's job. - Validate skill quality -- that is skill-reviewer's job. - Accept user-provided descriptions as a substitute for session scanning. Always scan first, then refine with user input. - Pre-judge which patterns are "worth it." Extract all candidates, let the user decide. - Skip checkpoints. Both approval gates are mandatory. ## Red Flags -- Recognize and Correct These thoughts mean the extraction is going off-track: | Impulse | Correction | |---------|------------| | "Let me just write the SKILL.md directly" | Stop. Hand off to skill-development. | | "This pattern isn't worth extracting" | Present it anyway. User decides value. | | "I'll skip the pattern brief and go straight to creation" | Stop. Brief first, approval second, handoff third. | | "The user described what they want, no need to scan" | Scan anyway. Session context adds nuance user descriptions miss. | | "skill-development failed, I'll create it myself" | Surface the error. Never bypass the pipeline. | | "One checkpoint is enough" | Both checkpoints are mandatory. No shortcuts. |
Related in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.