Claude Skills by allemaar

Propose a phased, gated implementation plan before any work begins. Trigger when the user runs /plan-create, says "make a plan", "plan this out", "design before coding", "let's plan first", "architect this", or asks for a phased approach before implementation. Also trigger proactively when a task is complex enough that jumping straight to execution would be risky — multi-file changes, new features, architectural shifts, refactors spanning multiple components, or any task where misalignment ea...

Phase-by-phase deep inspection of any multi-phase plan — stop at each phase and assess completeness, quality, and future-readiness before advancing. Trigger when the user runs /deep-dive or asks to "do a deep dive", "inspect each phase", "look at this more carefully", or "check if we're missing anything" on an existing plan. Use plan-create to create a new plan, plan-execute to run an approved plan, and plan-phases to add gates to a plan.

Evolve a target to its next version — treat what shipped as v1, plan the next iteration. The target can be a plan, a repo, a system, a document, a feature, or a skill. If a v1 plan artifact exists, evolve it; if not, the current state of the target IS v1. Trigger: 'what would v2 look like', 'evolve this', 'what's next for this', 'next iteration of this', 'plan the next version'. Use plan-deep-dive to inspect the current state, plan-execute to run the new plan, and plan-cleanup to remove artif...

Apply the last approved plan exactly. Trigger when the user runs /execute or says "execute the plan", "implement this", "do it", or "go ahead" after a plan has been approved. Surface judgment calls — do not make them silently. Not /plan-create (designs the plan first) or /plan-deep-dive (inspects a plan without running it) — plan-execute runs an already-approved plan.

Restructure an existing plan into phases with /verify gates after each phase and critical steps. Trigger when the user runs /phase-plan or asks to "add phases to this plan", "gate this plan", "restructure the plan", or "add checkpoints". Use plan-create for new plans and plan-deep-dive for inspection without restructuring.

Expand a vague gap into concrete questions + named source candidates via a delegated sub-agent — caller sees only the proposed pair for confirm/edit/refuse, never the expansion reasoning. Trigger /prime-expand, "expand on this", or auto-fire on handoff receipt with a thin brief. (Not for ambient "I need to know X" phrasing — that would collide with /investigate.) Single sub-agent, single turn, ≤3 candidate-source spot-checks only. Pairs with /prime-fetch (single noisy tool call) and /prime-sw...

Run a noisy data-fetching tool call (Grep, Glob, WebFetch, MCP search) on the caller's behalf in a sub-agent's context — only the filtered, proof-of-work-verified digest enters the caller's window. Trigger /prime-fetch, or when a planned tool call will return mostly noise. Single sub-agent, single wave, read-only tool calls only. Pairs with /prime-expand (clarify intent first) and /prime-sweep (multi-source investigation).

Prime the calling agent with high-signal context from large source surfaces (multiple files, packages, folders) via parallel delegated sub-agents. Sub-agents absorb the noise; only digested findings + source:line pointers enter the caller's context. Trigger /prime-sweep, chained from /prime-expand when sources are too large, or auto-fire on handoff receipt with listed sources. Iterative with cap 3 / log 4-6 / ask 7 / max 8 waves total. Pairs with /prime-expand (clarify intent first) and /prim...

Diagnose semantic repetition, filler, fake structure, stock AI rhetoric, and avoidable reading load in existing text. Trigger phrases: "/prose-audit", "find the AI filler", "audit this for bloat". Not for rewriting text; use /human-rewrite after diagnosis.

Lightweight cognitive pause — surface assumptions, uncertainty, and what you'd do differently. No gate, no enforcement, no artifacts required. Trigger when the user runs /reflect or wants to step back and think before continuing. Not /verify (formal gate) or /ask-gate (question triage) — reflect is freeform thinking with no gate.

EXPERIMENTAL capability-routing rubric — score a task on five task-readable axes (Risk, Uncertainty, Scope, Coupling, Verification) to derive WHO should execute (capability band 0–3) and HOW HARD they should try (volume 0–24), plus an evidence-derived plan gate. Recommends, never mandates; bands name ladder positions, never models, self-resolved from the runtime's own live roster; any doubt means session model. Trigger when the user runs /route-task, asks "which model should handle this", "ho...

The Self-Improvement Protocol (SIP). After a participating skill runs, detect concrete signals that the skill itself could be better — ambiguous instructions, an uncovered edge case, a misfired rule, a stale cross-reference, a user correction — and propose a specific diff to it, surfaced for approval and never auto-applied. Conservative by default: silent unless a ready, blocking, or recurring fix exists. Trigger via /self-improve, or automatically when a self-improvable skill completes. Not ...

The skills library menu — every skill grouped by family, each with a one-line description and a dual-doc/single-doc marker; pass a family name to drill into one family in full detail. Trigger with /skills-help, "list my skills", "which skill for X", "skills menu", "what skills do I have". Not /new-skill-creator (which scaffolds a new skill).

Opt-in installer that sets /synthesize as the standing output default in an agent's directive files (CLAUDE.md, AGENTS.md, or equivalent), telling each future session to load it before its first nontrivial reply — a standing instruction, not deterministic enforcement; the live skill's best-effort boundary for later turns stays as it is. Shows the exact per-file diff first, backs the file up, writes between managed markers, and reports how to undo. Trigger phrases: "/synthesize-init", "make sy...

Synthesize any agent output into a scannable, faithful, purpose-matched delivery. Append /synthesize to a brief to govern the pending output, or invoke it on an existing wall of text to restructure it. Designed for any subject and any reader. Trigger phrases: "synthesize this", "make this scannable", "I can't read this wall", "use the synthesize format".

Formal phase gate — checks intent, plan, and execution artifacts for drift, then actively re-checks each load-bearing claim against its source (an agent's self-report of having checked is not evidence). Requires the intent and execution artifacts (the plan is optional; an absent plan short-circuits to a plan-not-found verdict). Produces structured output. Trigger when the user runs /verify or needs to decide whether to proceed to the next phase. Not /double-check (quick re-check of one claim)...

Read, interpret, or explain existing YON content. Trigger on any .yon file, YON snippet (lines with @TAG|...|... patterns), or when the user says "read this YON", "what does this YON mean", "explain this @DOC/@RULE/@STEP", "summarize this YON", "interpret this record". Do NOT trigger for generic format questions ("what is YON?") with no YON content present — and do not trigger when the user wants to *write* YON (use yon-write).

YON Writing & Compilation Mode. Use when creating, generating, converting, or writing YON content. Triggers on: "write YON", "convert to YON", "create a .yon file", "encode this as YON", "YON format", or any request where the expected output is YON records. Also triggers when unstructured content should be structured into YON even without explicit keyword — e.g., working in a YON project. Use yon-read instead when reading, interpreting, explaining, or summarizing existing YON.

Identical in shape to `missing-footer-skill.md`, but the last block is the verbatim two-line blockquote. A green run here means the check read the file and found the footer, not that it never looked.

The body below opts into the contract by naming `human-output/SKILL.md`, so the footer is mandatory. What follows the citation is a PARAPHRASE, not the verbatim blockquote — which is exactly the drift a growing family produces.