product-on-purpose/thinking-framework-skills
Skill Claude CodeCodex
Generates several genuinely different framings of an ambiguous problem by varying altitude, stakeholder, and goal-versus-implementation, then selects the most useful one to solve and produces a reframed problem statement with How Might We angles. Use when a problem is vague, arrived as a symptom or a pre-baked…
product-on-purpose/thinking-framework-skills
Skill Claude CodeCodex
Evaluates rival causal explanations of a single case by typing each piece of within-case evidence by its diagnosticity (hoop, smoking-gun, straw-in-the-wind, doubly-decisive tests) against each rival's mechanism chain, then eliminating or confirming rivals item by item rather than by tallying. Use when one outcome has…
product-on-purpose/thinking-framework-skills
Skill Claude CodeCodex
Produces a pyramid that structures a recommendation answer-first - a single governing thought on top, a small set of MECE, deliberately ordered key arguments beneath it, and supporting evidence under each (Minto), with an optional SCQA intro framing. Use when a conclusion or recommendation already exists and must be…
product-on-purpose/writing-style-catalog
Plugin Claude Code
Composable writing instructions on four orthogonal axes (Voice, Tone, Style, Format): pick one entry per axis and the builder assembles a ready-to-paste prompt prefix that steers any LLM toward a precise register, reasoning pattern, and layout. Ships 97 curated entries, 1193 worked examples, 158 diff-pairs, and 14…
product-on-purpose/writing-style-catalog
Instructions file CodexOpenCode
AGENTS.md instructions for product-on-purpose/writing-style-catalog, covering agents.md - instructions for llms working in this repo, project purpose, the four-axis taxonomy model, key conventions and atomic-folder pattern.
product-on-purpose/writing-style-catalog
Instructions file
Claude Code instructions for product-on-purpose/writing-style-catalog, covering quick orientation, key commands, validate all entries (run before every commit), rebuild taxonomy.json (run after adding/editing entries) and hard rules.
product-on-purpose/writing-style-catalog
Skill Claude CodeCodex
Recommend a voice, tone, style, and format combination from the catalog's stable entries for a described writing situation, then compose the prompt in the same step. Accepts optional pre-fixed axis values; never recommends draft entries; reports low confidence rather than force-picking when nothing fits.
product-on-purpose/writing-style-catalog
Skill Claude CodeCodex
Guide a user to a personal writing-style profile - a saved selection across the catalog's Voice, Tone, Style, and Format axes - and prove it sounds like them with a generated sample before saving. Offers four intake modes (infer from your writing, recognize from examples, interview, or fill a template), confirms with…
product-on-purpose/writing-style-catalog
Skill Claude CodeCodex
Compose a writing instruction from voice, tone, style, and format entries you have already chosen. Returns a ready-to-paste LLM prompt prefix.
product-on-purpose/agent-skills-toolkit
Plugin Claude Code
Toolkit and Standard for authoring, validating, governing, and scaling cross-agent skill libraries (Claude Code and Codex) to a tiered Bronze/Silver/Gold quality bar. Use when building or grading agent skill plugins, when emitting components for multiple agents, or when adopting the Advanced Skill Library Standard.
product-on-purpose/agent-skills-toolkit
Instructions file CodexOpenCode
Instructions for product-on-purpose/agent-skills-toolkit, covering agents.md - agent-skills-toolkit, what this project is, current state (read before assuming capabilities), conventions and build / test / lint.
product-on-purpose/agent-skills-toolkit
Agent
Assesses a skill or plugin against the Advanced Skill Library Standard and reports findings with remediation. Use when delegating conformance assessment - the bounded read-only role behind askit-evaluate.
product-on-purpose/agent-skills-toolkit
Agent
Surveys a repository broadly and reports a structural map of its components and layout. Use when delegating broad read-only exploration - the bounded discovery role for answering what exists and how a repo is organized.
product-on-purpose/agent-skills-toolkit
Agent
Applies a specified set of file create and edit operations precisely, reading each target first. Use when delegating bounded file mutations - the role that carries out write and edit work an authoring skill has already decided on.
product-on-purpose/agent-skills-toolkit
Agent
Locates specific files, symbols, or text patterns and reports the matching paths and lines. Use when delegating a targeted search - the bounded read-only role for answering where something is, distinct from the broad survey askit-explorer runs.
product-on-purpose/agent-skills-toolkit
Agent
Judges whether a skill triggers and behaves correctly by running it against its eval-set and grading the outputs. Use when delegating a behavioral evaluation - the opt-in LLM-judge role behind askit-evaluate's behavioral mode, distinct from the deterministic conformance core.
product-on-purpose/agent-skills-toolkit
Agent
Reviews a component or a change for correctness, Standard conformance, and quality, and reports findings with severity. Use when delegating a judgment review that goes beyond the deterministic checks - the qualitative counterpart to askit-evaluator.
product-on-purpose/agent-skills-toolkit
Agent
Authors and improves agentskills.io skills to the Advanced Skill Library Standard. Use when delegating skill creation or conformance work - the bounded role behind askit-build-skill.
product-on-purpose/agent-skills-toolkit
Command
Create or improve an agentskills.io skill to the Advanced Skill Library Standard. Use to scaffold a new SKILL.md or raise an existing skill's conformance and description quality.
product-on-purpose/agent-skills-toolkit
Command
Evaluate a skill or plugin against the Advanced Skill Library Standard and report per-rule findings, the tier, and remediation. Use to audit conformance or see what blocks the next tier.
product-on-purpose/agent-skills-toolkit
Plugin Claude Code
Plugin marketplace listing 3 plugins: probe-agents-scan, probe-collision-a, probe-collision-b.
product-on-purpose/agent-skills-toolkit
Plugin Claude Code
PROBE FIXTURE, not a real plugin. Establishes whether Claude Code registers every .md under agents/. Deliberately ships README.md and README.md inside agents/.
product-on-purpose/agent-skills-toolkit
Agent
The only file in this directory that is meant to be a subagent. If the runtime registers exactly this one, the probe's recorded behaviour has CHANGED.
product-on-purpose/agent-skills-toolkit
Plugin Claude Code
PROBE FIXTURE, not a real plugin. One of two plugins shipping an identically named skill, to establish whether component names share a pool across plugins. This is side A.