CCFA Skills is a family of agent skills that helps researchers develop the storyline and presentation of CCF-A research papers. It supports work across research ideas, literature, experiments, writing, figures, reviews, rebuttals, and submission while keeping the argument connected. The catalogue entry consists of the project's research-writing skills and plugin.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mikubaka88/CCFA-Skills --skill ccf-idea-optimizergit clone --depth 1 https://github.com/mikubaka88/CCFA-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mikubaka88/ccfa-skills/ccf-idea-optimizer)<a href="https://agentmods.dev/skills/mikubaka88/ccfa-skills/ccf-idea-optimizer"><img src="https://agentmods.dev/badge/skills/mikubaka88/ccfa-skills/ccf-idea-optimizer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mikubaka88/ccfa-skills/ccf-idea-optimizer"><img src="https://agentmods.dev/badge/skills/mikubaka88/ccfa-skills/ccf-idea-optimizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00090 | $0.01263 |
| Opus 5 | $0.00045 | $0.00632 |
| Sonnet 5 | $0.00018 | $0.00253 |
| Haiku 4.5 | $0.00009 | $0.00126 |
Grade A, and why
ccf-idea-optimizer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CCF Idea Optimizer
Invocation Controls
CCFA Handoff Mode: PARTIAL (Recommended). Follow metadata.ccf_skill_controls.handoff_question_mode, ../ccf-common/references/handoff-modes.md, and ../ccf-common/references/task-modes.md. Complete requested idea development and necessary public-safe grounding under existing authorization. Do not load scoring, writing, or full experiment-design workflows unless their deliverables are requested or needed.
Core Rule
Turn a rough direction into a concrete problem, grounded gap, causal insight, mechanism, and falsifiable evidence plan. Distinguish source-backed observations from inferred opportunities. Do not invent prior work, results, reviewer sentiment, or novelty. Related work should clarify differentiation; an unsearched or crowded direction is uncertain, not automatically dead.
Preserve the user's theme and constraints. Vary framing or mechanism within the authorized development scope, and explain consequential changes. A useful idea has a coherent reason the intervention should change an observable result; a list of familiar modules is insufficient.
Modes
- Exploratory: develop rough seeds, find directions, and rescue promising ingredients before judging readiness.
- Quick: repair one local mechanism or give a concise idea card.
- Standard: ground a mature direction and produce a handoff-ready research plan.
Workflow
- Extract the user's decision, field, stage, resources, timeline, and available sources. Infer routine details and mark unknowns. Load
references/idea-intake.mdonly for messy or incomplete inputs; do not restart intake when the conversation already supplies them. - When venue fit matters, use
../ccf-common/references/ccf-a-venue-map.mdand the relevantreferences/venue-idea-adapters.mdpassage. An unspecified venue can use a labeled generic CCF-A lens. - Ground timeliness and closest work when needed for the request. Use
../ccf-common/references/privacy-and-evidence.mdbefore browsing; search public-safe terms. Useccf-literature-monitorfor recent-paper watch andccf-literature-searcherfor deeper retrieval. Honor no-browsing requests and label unsearched novelty accurately. - When sources are available, use
references/literature-grounded-evolution.mdto retain compact evidence cards, mechanism primitives, protocol anchors, and unresolved relations. Keep source locations rather than loading whole abstracts repeatedly. Trace borrowed ideas and inferred gaps separately. - For an underdetermined direction, use
references/frontier-ideation.mdto generate meaningfully different candidates. Three to five is a starting range, not a quota; one well-specified idea needs targeted improvement, not a forced tournament. Keep meaningful lineage and operations such as refine, combine, transfer, invert, or instrument internally. - Use
references/problem-method-blueprint.mdto connect problem, root challenge, insight, mechanism, assumptions, and expected observation. Check incompatible data assumptions, objectives, or resources. Keep the strongest route and a genuinely different fallback when useful. - Challenge the route against the closest-overlap concern and its weakest evidence link. Revise only for a material weakness; do not repeat self-critique that merely paraphrases the idea. Development selection can be internal; a requested assessment, including “靠谱吗” or “值得做吗” without scores, belongs to
ccf-idea-reviewer. - Use
references/experiment-design.mdto outline the minimum convincing evidence for the central claim: compatible datasets, baselines, metrics, and discriminating tests. A full execution protocol belongs toccf-experiment-designerwhen requested. Planned results remain predictions to test, not evidence. - Return the developed idea in the user's requested shape. For a weak seed, distinguish current weakness from development potential and identify a concrete rescue or reformulation before recommending abandonment. If a required decision remains open, explain the exact evidence needed and finish the independent parts.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 434 B
- references/experiment-design.md 3.5 KB
- references/frontier-ideation.md 3.9 KB
- references/idea-intake.md 3.5 KB
- references/literature-grounded-evolution.md 5.7 KB
- references/problem-method-blueprint.md 3.8 KB
- references/research-taste.md 3.1 KB
- references/source-notes.md 1.5 KB
- references/venue-idea-adapters.md 2.8 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago Changed · -57 lines · -3 tokens per session 8c997cd51453
- 11d ago First seen · 117 lines · 93 tokens per session scan A da3e73d9f3f6
ccf-idea-optimizer is a skill published in the GitHub repository mikubaka88/CCFA-Skills (2,395 stars, last pushed 4d ago), licensed MIT. It adds 90 tokens to every session and 1,263 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…