hraness
OrganizationA knowledge base for coding agents, built from Markdown, backlinks, semantic search, and Git context.
Categories
Indexed Skills (46)
phase-final-reviewer
End-to-end reviewer for a completed multi-phase feature at the end of a phase-orchestrator run. Use after all requested phases are finalized: inspects the whole feature against the plan and PRD/spec, hunting integration bugs across phase boundaries, missing acceptance criteria, stale plan state, and validation gaps. Patches only safe concrete issues; never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.
phase-implementer
Implements exactly one phase of a multi-phase plan during a phase-orchestrator run. Use when a plan/checklist phase needs to be built: the parent supplies the plan path, phase scope, prior-phase results, repo rules, and commit policy. Edits files directly; never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.
phase-orchestrator
Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and phase-final-reviewer skills and consumes plans in the write-phase-plan format. Use when the user provides a plan, checklist, PRD, or phase document and asks for delegated multi-agent execution across phases.
phase-reviewer
Reviews and fixes a just-implemented phase of a multi-phase plan during a phase-orchestrator run. Use after a phase's implementation and initial validation: checks the phase against the plan, PRD/spec, repo conventions, security, tenancy/data ownership, migrations, and test coverage, and patches bounded low-risk issues directly. Never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.
write-phase-plan
Writes or restructures an implementation plan in the format the phase-orchestrator skill consumes: dependency-ordered phases with explicit scope, acceptance criteria, validation commands, and status/log conventions. Use when the user asks to write a plan for phase orchestration, prepare a plan or PRD for delegated multi-agent implementation, or convert a spec, checklist, or design doc into implementable phases.
wordcell
Set up, evolve, or operate a hraness/wordcell local-first Markdown knowledge base for coding-agent memory. Use when a user asks to design Wordcell conventions or a recurring Wordcell ritual; search or query a Wordcell or Obsidian vault; load or recover repository context, plans, decisions, concepts, backlinks, semantic search, or Git provenance from an earlier coding session; save, clip, scrape, or archive a URL, article, social thread, signed-in browser page, or PDF as auditable Markdown; create or update a durable plan in the vault; or refresh, check, percolate, and maintain its knowledge graph. Do not use for generic web research, generic PDF reading, or ordinary planning that will not use a hraness/wordcell vault.
phase-final-reviewer
End-to-end reviewer for a completed multi-phase feature at the end of a phase-orchestrator run. Use after all requested phases are finalized: inspects the whole feature against the plan and PRD/spec, hunting integration bugs across phase boundaries, missing acceptance criteria, stale plan state, and validation gaps. Patches only safe concrete issues; never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.
phase-implementer
Implements exactly one phase of a multi-phase plan during a phase-orchestrator run. Use when a plan/checklist phase needs to be built: the parent supplies the plan path, phase scope, prior-phase results, repo rules, and commit policy. Edits files directly; never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.
phase-orchestrator
Orchestrates phase-based implementation plans using the host's todo tracker and subagents for implementation, review, validation, default phase commits, plan finalization, and a final end-to-end review. Delegates work through the companion phase-implementer, phase-reviewer, and phase-final-reviewer skills and consumes plans in the write-phase-plan format. Use when the user provides a plan, checklist, PRD, or phase document and asks for delegated multi-agent execution across phases.
phase-reviewer
Reviews and fixes a just-implemented phase of a multi-phase plan during a phase-orchestrator run. Use after a phase's implementation and initial validation: checks the phase against the plan, PRD/spec, repo conventions, security, tenancy/data ownership, migrations, and test coverage, and patches bounded low-risk issues directly. Never commits unless commit authority is explicitly delegated. Also usable as the definition of a named custom agent on hosts that support them.
write-phase-plan
Writes or restructures an implementation plan in the format the phase-orchestrator skill consumes: dependency-ordered phases with explicit scope, acceptance criteria, validation commands, and status/log conventions. Use when the user asks to write a plan for phase orchestration, prepare a plan or PRD for delegated multi-agent implementation, or convert a spec, checklist, or design doc into implementable phases.
soulscrape
Write a dated, cited dossier on one person from sources the user is allowed to use, keeping facts, stated beliefs, patterns, and speculation apart. Use when Claude Code, Codex, or another compatible agent is asked to understand, capture, or reconstruct a person; create a personal operating manual, master document, digital-twin or proxy bootstrap; extract worldview, values, taste, communication style, decisions, tensions, or tacit patterns; enrich a person with public research, verified profile links, or a sourced headshot and line portrait; or combine structured Soulscrape source packets from PeopleBlade or Message Like Me with notes, messages, posts, documents, repositories, and other evidence.
create-app-verifier
Create and prove a new project-local application-verifier Agent Skill that launches, health-checks, drives, observes, and safely cleans up the real application with a user-facing feature map. Use when a repository lacks an application verifier; do not use to maintain an existing verifier, write ordinary tests, or repair product behavior.
skillpack-admin
Use when auditing, adopting, checking drift in, or safely repairing this Hraness Agent Skills distribution. Do not use for Hraness apps or services, product coding, repository delivery, compute scheduling, or cloud execution.
phase-orchestrator
Execute an existing multi-phase repository plan with bounded implementation workers, independent review, join gates, validation, and final integration. Use when the user explicitly asks for delegated or multi-agent execution of a phase plan. Do not use for ordinary single-owner coding, plan authoring, semantic reasoning, or as a replacement for host scheduling and repo gates.
write-phase-plan
Write or restructure a dependency-ordered implementation plan for later multi-agent execution, with explicit phase ownership, acceptance criteria, validation, and status logging. Use when the user asks for a phased plan or a plan consumable by phase-orchestrator. Do not use to execute the plan or replace a repository's own planning and delivery rules.
assess-change-impact
Assess the direct and indirect blast radius of a proposed or existing code change, including callers, contracts, state, operations, and validation needs. Use when preparing to ship or when a small diff may have hidden effects; do not use to generate competing designs, explain an unchanged subsystem, or implement the change.
compare-approaches
Compare viable technical approaches against explicit constraints and evidence, producing a decision-ready recommendation. Use when a real architecture or implementation choice remains open; do not use when the answer is observable from the existing system, when one approach is already required, or to implement the winner.
docs-maintainer
Create or update repository documentation so commands, behavior, examples, navigation, and operational guidance match authoritative current sources. Use for README, guide, reference, runbook, or release-documentation maintenance; do not use for general copywriting, historical rationale, or product-code changes.
maintain-app-verifier
Audit and correct drift in an existing project-local application verifier, its driver, and references/features map using source and live evidence. Use when a verify-app skill already exists; do not use to create one, change product code, or treat a product regression as documentation drift.
performance-investigator
Diagnose and improve a measured performance problem using controlled baselines, profiling, hypotheses, and before/after evidence. Use for latency, throughput, CPU, memory, startup, rendering, or scaling regressions; do not use for unmeasured optimization, general refactoring, or infrastructure capacity planning.
reconstruct-rationale
Reconstruct why code, an API, or an architecture reached its current shape from version history and other authorized records, with calibrated confidence. Use for design-history and intent questions; do not use for a current-behavior walkthrough, speculative justification, or a change recommendation.
refactor-maintainer
Perform behavior-preserving structural changes with an explicit invariant, caller migration, deletion of obsolete paths, and focused plus repository-required validation. Use for refactors and internal migrations; do not use for feature work, intentional behavior changes, speculative cleanup, or performance changes without measurement.
repository-feature-map
Build or refresh a navigable, evidence-backed map of a repository's domains, entry points, runtime flows, data ownership, and validation surfaces. Use when someone needs orientation or a maintained repository map; do not use to explain one subsystem in depth, infer historical rationale, or assess a proposed change.
semantic-code-analysis
Explain how a code path or subsystem behaves now by tracing entry points, data flow, state, boundaries, failures, and verification evidence. Use for current-behavior questions; do not use to reconstruct historical intent, estimate change blast radius, or implement a fix.
test-engineer
Design, implement, or repair focused automated tests that reproduce behavior and provide reliable regression evidence at the right layer. Use for test strategy and test-code work; do not use to create an application-driving skill, perform performance tuning, or change product behavior beyond an explicitly requested fix.
analogy-transfer
Explicitly invoked semantic transform that imports mechanisms from structurally similar domains and checks where each analogy breaks. Use only when the user invokes $analogy-transfer. Do not use for ordinary repository analysis, coding, delivery, or orchestration.
assumption-audit
Explicitly invoked semantic audit of the load-bearing factual, causal, capability, people, continuity, and definitional assumptions in a claim or plan. Use only when the user invokes $assumption-audit. Do not route coding, repository review, delivery, or operations through this skill.
counterfactual
Explicitly invoked counterfactual reasoning that changes one fact, propagates consequences, and separates robust implications from speculation. Use only when the user invokes $counterfactual. Do not use for future planning, repository coding, delivery, or operational changes.
decision-matrix
Explicitly invoked semantic comparison of two to six named options using weighted criteria, reasoned scores, sensitivity, and a gut check. Use only when the user invokes $decision-matrix. Do not use to make repository, delivery, or operational changes.
dp-solve
Explicitly invoked semantic decomposition of a problem into overlapping subproblems whose answers can be reused and synthesized. Use only when the user invokes $dp-solve. This is a reasoning operator, not a request to write dynamic-programming code or perform repository delivery.
explanation-ladder
Explicitly invoked five-level explanation in which each level corrects, deepens, or reframes the prior one. Use only when the user invokes $explanation-ladder. Do not route documentation work, repository analysis, coding, delivery, or operations through this skill.
first-principles-thinking
Explicitly invoked semantic reconstruction from fundamental facts and hard constraints after removing inherited defaults and analogies. Use only when the user invokes $first-principles-thinking. Do not route ordinary coding, repository analysis, delivery, or operations through this skill.
golden-circle
Explicitly invoked semantic separation of purpose, method, and output into Why, How, and What, followed by a consistency check. Use only when the user invokes $golden-circle. Do not use for ordinary product implementation, repository delivery, or operations.
inversion
Explicitly invoked semantic inversion that derives safeguards by first asking how to guarantee failure. Use only when the user invokes $inversion. Do not use for repository, delivery, or operational changes.
joke
Explicitly invoked semantic transform from a topic or contradiction into an original compact joke with a compatible frame switch. Use only when the user invokes $joke. Do not route ordinary writing, coding, delivery, or operations through this skill.
ladder-of-abstraction
Explicitly invoked semantic movement between concrete instances, middle-level patterns, and governing principles. Use only when the user invokes $ladder-of-abstraction. Do not use for repository maps, code analysis, implementation, delivery, or operations.
lyric
Explicitly invoked semantic transform from a question, memory, or tension into an original poem or song lyric whose meaning emerges through image, sound, voice, and recurrence. Use only when the user invokes $lyric. Do not route ordinary writing, coding, delivery, or operations through this skill.
n-whys
Explicitly invoked why-chain exactly n levels deep across causal, conceptual, motivational, or philosophical explanations. Use only when the user invokes $n-whys; depth 5 replaces the former five-whys preset. Do not use for repository root-cause debugging, coding, delivery, or operations.
nietzche-ladder
Explicitly invoked three-stage Nietzschean explanation through Camel, Lion, and Child: inheritance, refusal, and creation. Use only when the user invokes $nietzche-ladder. Do not route coding, repository delivery, or operations through this semantic form.
parable
Explicitly invoked semantic transform from a question into a short original parable that embodies its tension without stating or settling it. Use only when the user invokes $parable. Do not route ordinary writing, coding, delivery, or operations through this skill.
question-forge
Explicitly invoked semantic transform that diagnoses a loaded, misplaced, or self-protective question and returns the harder question worth asking. Use only when the user invokes $question-forge. Do not use it to answer the question or perform repository coding, delivery, or operations.
sem-compile
Explicitly invoked compiler from a natural-language request, loose semantic pipeline, or existing program.md into an inspectable Sem program without executing it. Use only when the user invokes $sem-compile. Do not use it for repository coding, delivery, orchestration, shell, messaging, or other external effects.
sem-present
Explicitly invoked projection of one named existing Sem run into a bounded, validated view manifest without executing, resuming, or rendering the run. Use only when the user invokes $sem-present with an exact run directory. Do not use for repository visualization, coding, delivery, or operations.
sem-run
Explicitly invoked execution of a Sem program as isolated semantic applications with inspectable Markdown artifacts and a linked final result. Use only when the user invokes $sem-run and the host supports fresh no-history subagents. Do not use for repository coding, delivery, orchestration, shell work, messaging, or other external effects.
lifecharts
Create, inspect, and edit personal life timelines and career charts on Lifecharts from user-supplied facts, dates, résumés, or authorized profile material; return a verified chart link and lossless JSON.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.