skills/writing-research/creating-telegraph-pages/SKILL.md
Prepare and publish one explicitly authorized public Telegra.ph article through the official Telegraph API, including safe node conversion, optional account setup, credential handling, and page verification.
npx skillsauth add narumiruna/agent-skills creating-telegraph-pagesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use the bundled scripts/telegraph.py by absolute path. A page is a public external write. An exact request authorizes one page only when final title, content, and any byline/link are explicit; otherwise present those fields for approval before publishing. Account creation is a separate external-state change.
tag, optional attrs, and optional children.a, aside, b, blockquote, br, code, em, figcaption, figure, h3, h4, hr, i, iframe, img, li, ol, p, pre, s, strong, u, ul, or video. Attributes are string-valued href or src. Convert larger Markdown headings to h3/h4 and keep encoded content at or below 64 KB.Prefer TELEGRAPH_ACCESS_TOKEN from the user's secure environment. Never place a token in arguments, repository files, captured output, logs, or the response.
If no account exists, obtain separate approval for account creation, short name, and a new secret-file path. Then run:
uv run --no-project python "$SKILL_DIR/scripts/telegraph.py" create-account \
--short-name '<approved-name>' \
--token-file '<approved-secret-path>'
The helper refuses overwrite, uses owner-only permissions, and redacts token/auth URL output. Do not read the token through a captured-output tool or create replacement accounts to avoid credential recovery.
With exact publication authorization and SKILL_DIR resolved to this skill directory:
uv run --no-project python "$SKILL_DIR/scripts/telegraph.py" create-page \
--title '<approved-title>' \
--author-name '<approved-author-or-empty>' \
--author-url '<approved-author-url-or-empty>' \
/tmp/telegraph-content.json
Pass the approved byline values explicitly. To suppress account-default identity, include --author-name '' --author-url ''; omitting these fields can publish the account's default author name or URL. Inject the token through the execution environment and load an approved token file without printing it.
Require an https://telegra.ph/... result, then fetch or open the public page and verify title, byline, links, and content structure. Report the URL and any unavailable check. Remove sensitive temporary drafts after successful publication.
On invalid credentials, stop and request a valid token. Fix deterministic node validation errors before one retry; do not repeatedly retry ambiguous, rate, or service errors. Preserve enough error detail to diagnose without revealing secrets.
development
Score or compare one or more agent skills across trigger clarity, workflow actionability, safety boundaries, verification rigor, incremental knowledge value, and leanness. Use only when the user explicitly asks for ratings, numerical quality scores, rubric-based scorecards, or scored comparisons; use creating-agent-skills for unscored reviews or revisions.
development
Assess or improve an existing codebase's architecture when the user asks about module boundaries, coupling, scattered ownership, testability, change locality, deep modules, seams, or behavior-preserving structural refactoring. Use for cross-module design rather than ordinary diff review or a confirmed edge-case bug fix.
development
Perform read-only security audits, vulnerability assessments, or threat-focused reviews of diffs, pull requests, code paths, or explicitly scoped repositories when security is the primary objective or acceptance criterion. Use reviewing-code for ordinary review with baseline security coverage and hardening-code-paths for fixing confirmed findings.
development
Run iterative multi-reviewer panels over a code diff, verify their findings, apply explicitly authorized fixes, and re-review the updated change until it passes or reaches a stopping condition. Use when the user asks for a panel loop, multi-model code-review consensus, or a review-fix-re-review cycle.