Agent skill

Ccf Humanization

by mikubaka88 in mikubaka88/CCFA-Skills

Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance.

MITAuto-check passed

Install Ccf Humanization

skills CLI
$ npx skills add mikubaka88/CCFA-Skills --skill ccf-humanization -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mikubaka88/CCFA-Skills ccf-humanization --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mikubaka88/CCFA-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ccf-humanization .claude/skills/ccf-humanization && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ccf-humanization
GitHub stars
3k
Token cost
~2k tokens
SKILL.md length
911 words
Files
4 (incl. references)
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance.

  • Works in 8 steps: Identify the requested artifact,… → Recover each paragraph's scientific… → Remove repeated caveats across sections.… → …
  • SKILL.md covers Family File Contract, Collaboration Contract, Invocation Controls and Family Baseline, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ccf Humanization is an agent skill from mikubaka88/CCFA-Skills. Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance. Keep reasoning and communication direct, remove empty defensive framing, and preserve evidence and uncertainty. Also use for 去防御性 and 论文人性化. Apply prose edits only within the authorized task; specialist skills retain ownership.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/experiment-discipline.md` and `references/humanization-policy.md`).

The repository describes itself as: A skill family for shaping the research storyline of CCF-A papers. The licence is MIT.

Example prompts

  • “/ccf-humanization”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Identify the requested artifact, existing authorization, and whether the input is prose, a proposed design, or reported results. Read…
  2. Recover each paragraph's scientific message. State the observation, operation, assumption, or inference directly. Delete empty…
  3. Remove repeated caveats across sections. Express scope where it changes interpretation; do not require every abstract, paragraph, caption…
  4. Preserve material facts and calibrated uncertainty in the authorized edit. If a decision requires new evidence or a research-scope change…
  5. For actual publication comparisons or executable experiment changes, load references/experiment-discipline.md. Preserve a verified…
  6. Apply the existing punctuation and terminology preferences after the scientific argument is sound. For full sections or papers, run…
  7. Read the final prose once. Check that rhetorical caution has not been replaced by hype, factual omission, or a different scientific claim…
  8. Return the requested artifact in its original format. When acting as a sidecar, return ownership to the content skill; do not append a…

What it can do on your machine

Read from SKILL.md and the folder at commit 5969e6b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ccf Humanization loads about 2k tokens when it runs, and up to ~6.1k if it reads all its reference files. Until then it costs about 93 tokens; SKILL.md has 911 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mikubaka88/CCFA-Skills at commit 5969e6b, republished under its MIT licence (© mikubaka88). 911 words, ~2,022 tokens.

Download SKILL.mdSave it as .claude/skills/ccf-humanization/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
ccf-humanization
description
Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance. Keep reasoning and communication direct, remove empty defensive framing, and preserve evidence and uncertainty. Also use for 去防御性 and 论文人性化. Apply prose edits only within the authorized task; specialist skills retain ownership.

CCF Humanization

Family File Contract

Before writing, resolve the canonical output and one stable working directory per task/artifact. Reuse explicit or established task paths; otherwise use project-root ccfa-workfiles/<purpose>/<artifact-id>/, with source/, assets/, cache/, and build/ only as needed. Update current files in place; do not scatter intermediates or create iteration copies. Preserve inputs and required evidence; clean only verified disposable files created by this task. Use UTF-8 text I/O and check Chinese text after saving or rendering. For file work, apply artifact-contracts.md and reuse the same paths across skill transitions.

Collaboration Contract

This is the first required family preflight. Apply the baseline below, then activate ccf-common before specialist work. The two preflights bootstrap once without recursively re-entering each other; reuse applicable rules across contributors.

Keep one integrating owner and actively use other skills to resolve missing prerequisites or check material findings. Reuse applicable evidence; do not skip necessary groundwork to save tokens. Before finalizing, integrate contributions and verify affected results. Follow the conditional cooperation routes; avoid unrelated stages and duplicate reports.

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.

Activate this first for every CCFA task and contributor, including planning, retrieval, review, auditing, rendering, scaffolding, and maintenance. Apply the family baseline below before ccf-common and specialist execution. Reuse an already loaded, applicable baseline at handoffs; refresh changed or lost rules. Prose editing and experiment checks depend on the actual task, but baseline activation is universal. Specialist skills retain ownership and explicit user/host constraints still apply.

Family Baseline

Read and apply this entry's baseline before specialist work. Communicate the concrete task, evidence, and decisions directly; avoid imagined objections, empty assurances, repetitive warnings, and unnecessary process narration. Preserve real risks, critical review findings, uncertainty, scientific facts, source quotations, and mandatory checks. Do not turn critical assessment into praise or change scores to sound less defensive. Review-only tasks diagnose without rewriting; non-prose tasks apply these rules without inventing a prose-edit pass. Enable only relevant detailed modes below. This preflight creates no report, warning file, or separate agent by default.

Core Rule

Write the scientific argument directly: problem, insight, mechanism, evidence, and supported implication. Remove authorial self-defense, imagined reviewer objections, apologetic novelty positioning, denial-led statements, empty assurances, stacked hedging, repeated scope disclaimers, and obligatory cautionary endings. Replace a defensive sentence with its scientific payload or delete it if it adds none.

Humanization preserves rigor: retain meaningful uncertainty, actual assumptions, negative results, protocol facts, citations, equations, numbers, terminology, and required disclosures. Do not turn suggests into proves, omit a known failure, or hide a real comparison limitation. Do not treat isolated words such as only, not, or may as errors.

Keep method confirmation and version-gate status internal. Describe the actual method and relevant configuration naturally. Use supplied specifications for method drafting, cited evidence for prior work, and verified full configurations for reported comparisons; do not require new experiments just to edit supported prose.

Modes

  • family-preflight: always apply the baseline before any CCFA specialist; no manuscript or experiment artifact is required.
  • manuscript-humanization: revise defensive prose while preserving scientific content and source format.
  • experiment-humanization: apply the same prose standard to final experiment descriptions and tables; preserve full-method comparisons and labeled ablations.
  • warning-only: identify a concrete unresolved scientific decision without modifying its dependent artifact.
Show full SKILL.md (372 more words)Show less

Workflow

For family-preflight, apply the baseline, ensure ccf-common is active, and continue the requested specialist task. The following editing workflow applies only when the task includes relevant prose or experiment artifacts; do not run it merely to complete the universal preflight.

  1. Identify the requested artifact, existing authorization, and whether the input is prose, a proposed design, or reported results. Read references/humanization-policy.md for the sentence decisions and bilingual repair examples.
  2. Recover each paragraph's scientific message. State the observation, operation, assumption, or inference directly. Delete empty self-defense instead of moving it into a warning block.
  3. Remove repeated caveats across sections. Express scope where it changes interpretation; do not require every abstract, paragraph, caption, or conclusion to end with a limitation.
  4. Preserve material facts and calibrated uncertainty in the authorized edit. If a decision requires new evidence or a research-scope change, isolate that decision and continue unaffected work. Do not edit a source file merely to encode a warning.
  5. For actual publication comparisons or executable experiment changes, load references/experiment-discipline.md. Preserve a verified identity and full configuration in the internal gate; keep legitimate ablations clearly labeled. Run this step only when the task needs it.
  6. Apply the existing punctuation and terminology preferences after the scientific argument is sound. For full sections or papers, run ../ccf-paper-writer/scripts/check_prose_quality.py when available and inspect its candidate locations in context. Do not rewrite correct scientific language merely to clear a heuristic warning.
  7. Read the final prose once. Check that rhetorical caution has not been replaced by hype, factual omission, or a different scientific claim. Rerun a check only for changed text or an unresolved finding.
  8. Return the requested artifact in its original format. When acting as a sidecar, return ownership to the content skill; do not append a process report to ordinary prose.

Warning Contract

Use only for a concrete decision that cannot be resolved from supplied evidence and existing authorization:

text
CCF Humanization Warning: not inserted into artifacts
Affected claim / file / experiment:
Evidence gap and material consequence:
Decision needed:
Materiality: advisory / blocking
File changes made for this warning: none

blocking applies to the dependent claim or change, not the entire task. Style choices, already documented limitations, and accurate local claim narrowing are ordinary authorized edits.

References

  • references/humanization-policy.md: direct scientific voice, sentence/paragraph repair, bilingual examples, material facts, warning-only decisions, punctuation, and checksum policy.
  • references/experiment-discipline.md: full-method comparisons, supplied specifications, ablations, and proportionate smoke checks.

© mikubaka88, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references) in ccf-humanization of mikubaka88/CCFA-Skills.

  • SKILL.md
  • agents/openai.yaml
  • references/experiment-discipline.md
  • references/humanization-policy.md

Open the folder on GitHubat commit 5969e6b

Compare with similar skills

Ccf Humanization next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ccf Humanization compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ccf Humanization this skillmikubaka88/CCFA-Skills3k—~2kAutomated safety check: PassMIT
Humanizebrycewang-stanford/Auto-Empirical-Research-Skills4.5k—~6.6kAutomated safety check: PassCustom licence
Humanize Chinesesickn33/agentic-awesome-skills47k2 repos~1.3kAutomated safety check: PassMIT
Human Gatealirezarezvani/claude-skills28k—~1.5kAutomated safety check: PassMIT
HumanizerPrism-Shadow/penguin-harness2.5k—~1.8kAutomated safety check: PassApache-2.0
Requirementsrizsotto/Bear6.5k—~2kAutomated safety check: PassGPL-3.0

Similar skills

  • Humanize

    brycewang-stanford/Auto-Empirical-Research-Skills

    Humanization Pipeline Orchestrator v3.1 - Multi-pass 4-layer transformation pipeline Orchestrates G5 (Auditor), G6 (Humanizer), F5 (Verifier) in sequential passes Enforces checkpoints between every…

    4.5k GitHub stars~6.6k tokensUpdated 4 days ago
    Writing & ContentAuto-check passed
  • Humanize Chinese

    sickn33/agentic-awesome-skills

    Detect and rewrite AI-like Chinese text with a practical workflow for scoring, humanization, academic AIGC reduction, and style conversion.

    47k GitHub starsUsed in 2 repos~1.3k tokens
    Writing & ContentAuto-check passed
  • Human Gate

    alirezarezvani/claude-skills

    Runs the human-verification lane of an agent loop, and proves review happened before work is called done.

    28k GitHub stars~1.5k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check passed
  • Humanizer

    Prism-Shadow/penguin-harness

    Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output.

    2.5k GitHub stars~1.8k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Requirements

    rizsotto/Bear

    Write, modify, or review a requirement file under docs/requirements -- pick the single owning file, keep the text contract-only, name IDs so they need no explanation, and verify cross-references and…

    6.5k GitHub stars~2k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Humanizer

    LeoYeAI/openclaw-master-skills

    Humanize AI-generated text by detecting and removing patterns typical of LLM output.

    2.2k GitHub stars~2k tokensUpdated 2 mo ago
    Writing & ContentAuto-check passed

More from mikubaka88/CCFA-Skills

All 17 skills in this repo
  • Ccf Paper Reviewer

    mikubaka88/CCFA-Skills

    Review manuscript claims, evidence, and writing without rewriting.

    3k GitHub stars~3k tokensUpdated 23 days ago
    Auto-check passed
  • Ccf Rebuttal Writer

    mikubaka88/CCFA-Skills

    Write CCF rebuttals, author responses, revision ledgers, response letters, and conservative resubmission plans.

    3k GitHub stars~1.6k tokensUpdated 23 days ago
    Auto-check passed
  • Ccf Common

    mikubaka88/CCFA-Skills

    Required shared preflight for every CCFA skill after ccf-humanization: apply routing, scope, prerequisites, evidence rules, handoffs, and artifact contracts.

    3k GitHub stars~1.8k tokensUpdated 23 days ago
    Auto-check passed
  • Ccf Experiment Designer

    mikubaka88/CCFA-Skills

    Design CCF experiment protocols and evidence schemas: datasets, baselines, metrics, ablations, and result-table contents.

    3k GitHub stars~1.9k tokensUpdated 23 days ago
    Auto-check passed
  • Ccf Literature Monitor

    mikubaka88/CCFA-Skills

    Scan recent arXiv/OpenReview papers, venue feeds, labs, and competitors for overlap.

    3k GitHub stars~1.8k tokensUpdated 23 days ago
    Auto-check passed
  • Ccf Literature Searcher

    mikubaka88/CCFA-Skills

    Find and verify external literature, prior art, datasets, benchmarks, and citation candidates.

    3k GitHub stars~3.1k tokensUpdated 23 days ago
    Auto-check passed

Questions about Ccf Humanization

What does Ccf Humanization do?

Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance. Ccf Humanization is an agent skill from mikubaka88/CCFA-Skills. Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance.

How do I install Ccf Humanization in Claude Code?

Run `npx skills add mikubaka88/CCFA-Skills --skill ccf-humanization -a claude-code`. Or copy the skill folder (ccf-humanization in mikubaka88/CCFA-Skills) into .claude/skills/ccf-humanization in your project. Claude Code loads it when a task matches its description.

How do I install Ccf Humanization in Codex?

Run `npx skills add mikubaka88/CCFA-Skills --skill ccf-humanization -a codex`. Or copy the skill folder (ccf-humanization in mikubaka88/CCFA-Skills) into .agents/skills/ccf-humanization in your project. Codex loads it when a task matches its description.

Can I use Ccf Humanization in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mikubaka88/CCFA-Skills --skill ccf-humanization -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ccf-humanization, .gemini/skills/ccf-humanization, .github/skills/ccf-humanization and .opencode/skills/ccf-humanization in your project.

What does Ccf Humanization need to run?

SKILL.md names no scripts, command-line tools or credentials: Ccf Humanization is instructions for the agent only.

Does Ccf Humanization access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ccf Humanization safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ccf Humanization use?

Ccf Humanization is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ccf Humanization use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.1k tokens, read only when the agent opens those files.

What are the alternatives to Ccf Humanization?

Skills that share tags, products or a category with Ccf Humanization: Humanize (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars), Humanize Chinese (sickn33/agentic-awesome-skills, 47k stars), Human Gate (alirezarezvani/claude-skills, 28k stars) and Humanizer (Prism-Shadow/penguin-harness, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ccf Humanization?

mikubaka88 (a GitHub user) maintains it in mikubaka88/CCFA-Skills, which has 3,001 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 16, 2026.

Source: mikubaka88/CCFA-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.