Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/roi-danino-blog-entry
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/blog-entry
What's inside
- Skill name
blog-entry- Description
- Write a new Feather Browser blog entry. Gathers context from session records, writes a complete first-person draft in Roi's voice, presents it for review. Use when a phase exit triggers the blog cadence, or when a significant decision lands.
- License
- Apache-2.0
- Instructions
- 48 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Blog Entry Write a complete draft for `blog/`. Present it to Roi for review. He approves or adjusts the whole piece — no step-by-step check-ins. ## 1. Gather context Read these sources in order to reconstruct the story without having been in those sessions: 1. `.remember/remember.md` — session handoff, what completed, what's next 2. Find the last blog commit to set the lower bound: `git log --oneline --all -- blog/` (top line) — note its date. 3. **Every `journal/ops/sessions/` file written since that last blog entry** — the detailed stop record for *each* session in the arc this entry covers, not just the last one. The filename timestamp tells you which are newer than the last blog entry; read them oldest → newest. (If none are newer — no sessions since the last entry — read just the most recent file.) This is what keeps a multi-session phase from collapsing into only its final session. 4. `git log --oneline -20` — commit trail since the last blog entry 5. Last 15 lines of `journal/log.md` — JSONL-style work log with timestamps 6. `blog/README.md` — last entry's milestone, so the new entry advances the story ## 2. Voice guardrails Entry 0001 (`blog/0001-the-story-so-far.md`) and entry 0002 (`blog/0002-write-it-down-or-it-didnt-happen.md`) are the gold standard. Match this voice: - **First-person (Roi).** Write as him, not about him. - **Honest over polished.** Say what actually happened, including inconclusive results and things that didn't work. - **Hero's journey.** There's a before, a challenge or decision, and a new position. Not a changelog. - **Plain language.** If a technical term appears, either explain it in one clause or don't use it. The audience is builders, not necessarily engineers. - **AI-collaboration is a thread, not a headline.** The story is Feather; "I direct, the AI builds" is the method, mentioned where it's relevant, not foregrounded. - **Anchored to a real milestone or decision.** Every entry maps to something concrete — a merged phase, an ADR, a spike result. No entries about intentions. - **Short paragraphs.** Two to four sentences each. White space is part of the voice. ## 3. Completeness checklist Before presenting the draft: - [ ] Frontmatter complete: `title`, `date`, `entry` (next number from README), `milestone`, `maps_to` (ADR slugs or plan paths), `tags`, `status: published` - [ ] Opening hook earns the read — one or two sentences that pull in a non-technical person - [ ] Narrative arc present: why we got here → what happened → where we are now - [ ] Each section heading is a phrase, not a label (e.g. "The decisions" not "ADR Summary") - [ ] LinkedIn cut at the end — scroll-stopping first line, 4–6 bullet points, relevant hashtags - [ ] `blog/README.md` entry table updated with new row ## 4. File naming `blog/NNNN-slug-from-title.md` — next number in sequence, slug is kebab-case title. ## 5. Commit After Roi approves: commit blog entry + README update together. Commit message: `blog(NNNN): <title>`
From ROI-DANINO/feather-browser, Apache-2.0.
More from ROI-DANINO/feather-browser
- 0.474score
using-feather-browser
ROI-DANINO
Use whenever an agent will drive a website through the Feather Browser HTTP API — creating a session, navigating, clicking, typing, reading a page, or…
SkillCFreshness: CClaude Code +9 - 0.474score
feather-data-extraction
ROI-DANINO
Use when reading or scraping content from a web page through Feather Browser — pulling text, links, structured fields, or a list of items.
SkillCFreshness: CClaude Code +9 - 0.474score
feather-form-filling
ROI-DANINO
Use when filling out a web form through Feather Browser — signup, login, checkout, multi-field input, dropdowns, date pickers, or any "enter these values and…
SkillCFreshness: CClaude Code +9 - 0.474score
feather-human-handoff
ROI-DANINO
Use when a Feather Browser task needs a human to step in — solving a CAPTCHA, completing MFA/2FA, approving a consent dialog, or any step the agent literally…
SkillCFreshness: CClaude Code +9 - 0.471score
feather-operator
ROI-DANINO
How to drive Feather Browser over its local HTTP API — endpoint discovery, the golden loop, element targeting, sessions/profiles, honest result reporting.
SkillCFreshness: CClaude Code +9 - 0.470score
integrating-providers
ROI-DANINO
Adds new AI providers to claude-council, configures provider API settings, troubleshoots provider connections, and documents the provider script interface.
SkillCFreshness: CClaude Code +9 - 0.470score
querying-council-with-agents
ROI-DANINO
Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions…
SkillCFreshness: CClaude Code +9 - 0.469score
research
ROI-DANINO
Use when encountering an unfamiliar API, a potential better approach, a library update, an error pattern, or any technical uncertainty that warrants…
SkillCFreshness: CClaude Code +9 - 0.469score
fb-stop
ROI-DANINO
Feather Browser /stop command.
SkillCFreshness: CClaude Code +9 - 0.464score
fb-start
ROI-DANINO
Feather Browser /start command.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/ROI-DANINO/feather-browser
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ROI-DANINO
- 0.474score
feather-data-extraction
ROI-DANINO
Use when reading or scraping content from a web page through Feather Browser — pulling text, links, structured fields, or a list of items.
SkillCFreshness: CClaude Code +9 - 0.474score
feather-human-handoff
ROI-DANINO
Use when a Feather Browser task needs a human to step in — solving a CAPTCHA, completing MFA/2FA, approving a consent dialog, or any step the agent literally…
SkillCFreshness: CClaude Code +9 - 0.474score
using-feather-browser
ROI-DANINO
Use whenever an agent will drive a website through the Feather Browser HTTP API — creating a session, navigating, clicking, typing, reading a page, or…
SkillCFreshness: CClaude Code +9 - 0.474score
feather-form-filling
ROI-DANINO
Use when filling out a web form through Feather Browser — signup, login, checkout, multi-field input, dropdowns, date pickers, or any "enter these values and…
SkillCFreshness: CClaude Code +9 - 0.471score
feather-operator
ROI-DANINO
How to drive Feather Browser over its local HTTP API — endpoint discovery, the golden loop, element targeting, sessions/profiles, honest result reporting.
SkillCFreshness: CClaude Code +9 - 0.470score
querying-council-with-agents
ROI-DANINO
Executes agent-enhanced council queries by spawning parallel Claude subagents that each query a provider, evaluate response quality, ask follow-up questions…
SkillCFreshness: CClaude Code +9
Cite this page
blog-entry skill. Agent Mart. https://agentmart.dev/skills/roi-danino-blog-entry (last updated 2026-10-24)