architecture
01Skill Claude CodeCodex
Use when a file or module is too large, responsibilities are tangled, or a cross-cutting redesign is needed.
47 5mo ago A 24 tokens
original MIT
47Stars on the repository
27Mods indexed here, across every type
5mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Skill Claude CodeCodex
Use when literature notes exist and need citation verification, or before publishing any artifact that cites literature.
47 5mo ago A 22 tokens
original MIT
Skill Claude CodeCodex
Use at the end of a work session to embed learnings into conventions. Simplified for models with lower reasoning capacity.
47 5mo ago A 27 tokens
original MIT
compound
04Skill Claude CodeCodex
Use at the end of a work session, or when accumulated findings need to be embedded into conventions, skills, or patterns.
47 5mo ago A 26 tokens
original MIT
coordinator
05Skill Claude CodeCodex
Use when the Slack bot needs to handle an operational action like launching an experiment, querying status, or processing approvals.
47 5mo ago A 25 tokens
original MIT
critique
06Skill Claude CodeCodex
Use when a plan, finding, or design needs adversarial review before committing to it.
47 5mo ago A 20 tokens
original MIT
design
07Skill Claude CodeCodex
Use when designing a new experiment or research protocol and need to ensure methodological rigor.
47 5mo ago A 17 tokens
original MIT
develop
08Skill Claude CodeCodex
Use when implementing new features, fixing bugs, or modifying code in infra/.
47 5mo ago A 17 tokens
original MIT
diagnose
09Skill Claude CodeCodex
Use when experimental results are unexpected, confusing, or need interpretation.
47 5mo ago A 15 tokens
original MIT
feedback
10Skill Claude CodeCodex
Use when the PI or a human provides feedback, corrections, or direction on agent work.
47 5mo ago A 19 tokens
original MIT
gravity
11Skill Claude CodeCodex
Use when a manual fix or workaround keeps recurring and might need to be formalized into infrastructure.
47 5mo ago A 20 tokens
original MIT
horizon-scan
12Skill Claude CodeCodex
Use when akari needs to proactively scan for new GenAI developments — model releases, capability changes, relevant research — rather than waiting for human input.
47 5mo ago A 34 tokens
original MIT
lit-review
13Skill Claude CodeCodex
Use when a research topic needs literature review, or when papers need to be found and documented for a project.
47 5mo ago A 24 tokens
original MIT
Skill Claude CodeCodex
Use at the start of a work session to select a task. Simplified for models with lower reasoning capacity.
47 5mo ago A 25 tokens
original MIT
orient
15Skill Claude CodeCodex
Use at the start of every work session to assess current state and select the highest-value task.
47 5mo ago A 20 tokens
original MIT
postmortem
16Skill Claude CodeCodex
Use when an agent produced a flawed output and you need to understand why the reasoning went wrong.
47 5mo ago A 22 tokens
original MIT
project
17Skill Claude CodeCodex
Create new research projects — either propose (agent-initiated gap analysis → formal proposal) or scaffold (human-initiated interview → project directory).
47 5mo ago A 32 tokens
original MIT
publish
18Skill Claude CodeCodex
Use when a paper draft exists and needs to be prepared for venue submission or arxiv preprint.
47 5mo ago A 21 tokens
original MIT
Skill Claude CodeCodex
Use when skills may be out of date with source code, after significant infra changes, or when skill descriptions need CSO compliance audit.
47 5mo ago A 30 tokens
original MIT
report
20Skill Claude CodeCodex
Use when a status report, research digest, or experiment comparison is needed for human review.
47 5mo ago A 19 tokens
original MIT
review
21Skill Claude CodeCodex
Validate experiment metrics and findings — run metrics-first to check computations are meaningful, then findings to check conclusions are valid.
47 5mo ago A 24 tokens
original MIT
self-audit
22Skill Claude CodeCodex
Use when sessions have committed code and you need to check compliance with CLAUDE.md conventions, log entry standards, and experiment validation.
47 5mo ago A 30 tokens
original MIT
simplify
23Skill Claude CodeCodex
Use when a plan or implementation feels over-engineered and needs a complexity check.
47 5mo ago A 18 tokens
original MIT
Skill Claude CodeCodex
Use when a Slack thread shows the bot behaving incorrectly and the root cause needs investigation.
47 5mo ago A 22 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: