Menu
SkillsMP a collecté 40 skills depuis Green-PT/honey-for-devs. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 40.
Honey for plain Claude — the terse-prose core with no agent-harness features. Paste into a claude.ai Project's custom instructions, a Style, or an API system prompt. Strips filler, hedging, and pleasantries from every response while keeping facts, names,…
Langue du texte source : anglais
Compress-Cache-Retrieve for huge, repetitive array tool output (logs, scan results, time series, event streams) before it enters context. Keeps an informative sample — endpoints, anomalies/change-points, head/tail — drops the redundant rest to a local cache,…
Langue du texte source : anglais
Rewrite a memory or context file (CLAUDE.md, AGENTS.md, a todo or notes file) into Honey-terse form so it costs fewer input tokens every session, without losing meaning. Backs up the original first. Use when asked to shrink or compress context files, trim…
Langue du texte source : anglais
Harvest every `honey:` comment in the codebase into a debt ledger, so the deliberate shortcuts Lever 1 leaves behind get tracked instead of rotting into "later means never". Flags markers with no revisit trigger — those are the ones that go permanent…
Langue du texte source : anglais
Same pixels, fewer tokens — for user-facing deliverables where visual polish is the spec. Use when building or editing a landing page, marketing site, hero, pricing/feature section, dashboard, or any HTML/CSS UI component. Keeps the full rendered design…
Langue du texte source : anglais
Report this session's output tokens and CO₂ by running the repo's committed EcoLogits port, plus the modelled CO₂/$ saved vs a no-Honey baseline — always labelled with the bench stamp it came from. Use when asked how much Honey saved, the session's…
Langue du texte source : anglais
Show Honey's benchmark scoreboard — the committed quality and token results per task tier (code, user-facing, agent-to-agent) from bench/. Reports only the reproducible committed figures, never invents per-repo numbers. Use when asked how much Honey saves,…
Langue du texte source : anglais
Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3).…
Langue du texte source : anglais
Cost discipline for recurring /loop runs. A loop multiplies per-iteration cost by iteration count, so waste compounds. Encodes cache-aware pacing (avoid the 300s dead zone), event-driven-over-polling, a no-change short-circuit, a compact state handle carried…
Langue du texte source : anglais
Create and maintain one committed per-project memory file (PROJECT.md) so agents stop re-discovering the same facts every cold session. Stores only the stable, expensive-to-rediscover, not-in-the-code context — architecture + why, build/test/run commands,…
Langue du texte source : anglais
Read huge, dense, read-only text as rendered PNG pages instead of raw text — image tokens scale with pixels, not characters, so token-dense bulk (big files, vendored code, diffs, logs) costs ~60–75% less as an image. Use when you must skim or reason over…
Langue du texte source : anglais
Review a diff for what Honey would cut — over-engineering (speculative generality, hand-rolled stdlib, single-caller abstractions) and over-verbosity (dead code, narration, redundant comments). Outputs a terse delete-list, one line per finding, with the line…
Langue du texte source : anglais
Write less code and say less about it. Applies YAGNI and stdlib/native-first so the agent writes the minimum code that needs to exist, and responds tersely — stripping filler, hedging, and pleasantries while keeping code, identifiers, and technical terms…
Langue du texte source : anglais
Stack Honey onto Superpowers-style workflows (subagent-driven-development, dispatching-parallel-agents, executing-plans) and any orchestration that dispatches fresh subagents. Dispatched subagents run in isolated context and do NOT inherit the session's Honey…
Langue du texte source : anglais
Compress-cache-retrieve huge array tool output.
Langue du texte source : anglais
Rewrite context files terse to cut per-session tokens.
Langue du texte source : anglais
Harvest honey shortcut markers into a debt ledger.
Langue du texte source : anglais
Same pixels, fewer tokens: dense CSS for user-facing UI.
Langue du texte source : anglais
Report session token and CO2 savings vs no-Honey baseline.
Langue du texte source : anglais
Honey benchmark scoreboard vs baseline and rival skills.
Langue du texte source : anglais
Delegate search/review to subagents; compressed returns.
Langue du texte source : anglais
Cost discipline for recurring loop runs.
Langue du texte source : anglais
Per-project persistent memory files indexed in MEMORY.md.
Langue du texte source : anglais
Read huge read-only text as PNG pages; big input cut.
Langue du texte source : anglais
Review a diff for over-engineering; terse delete-list.
Langue du texte source : anglais
Write less code and say less about it. Cuts token cost.
Langue du texte source : anglais
Inject Honey levers into dispatched subagent prompts.
Langue du texte source : anglais
Harvest every `honey:` shortcut marker into a debt ledger, flagging the ones with no revisit trigger. One-shot report, changes nothing.
Langue du texte source : anglais
Show Honey's benchmark scoreboard: committed quality and token results per task tier vs Caveman, Ponytail, and no-skill. One-shot.
Langue du texte source : anglais
Write less code and say less about it: YAGNI, stdlib-first, terse prose. Cuts agent token cost on every coding and writing task.
Langue du texte source : anglais
Report the session's Honey savings: output tokens, CO2, and CO2/$ saved vs a no-Honey baseline, via the committed EcoLogits port.
Langue du texte source : anglais
Compress-Cache-Retrieve huge repetitive array tool output before it hits context: keep a sample, cache the rest, leave a hash.
Langue du texte source : anglais
Read huge dense read-only text as PNG pages via pxpipe export: ~60-75% fewer input tokens. Lossy on exact strings; never for files you will edit.
Langue du texte source : anglais
Delegate search- and review-heavy work to Honey's read-only subagents so large reads return compressed instead of bloating context.
Langue du texte source : anglais
Cost discipline for recurring /loop runs: cache-aware pacing, event-driven-over-polling, no-change short-circuit, compact state handle, stop condition.
Langue du texte source : anglais
Stack Honey onto Superpowers-style subagent workflows: dispatched subagents skip the session hook, so inject the levers into each dispatch prompt.
Langue du texte source : anglais
Rewrite a memory or context file (CLAUDE.md, AGENTS.md, notes) into Honey-terse form to cut per-session input tokens. Backs up first.
Langue du texte source : anglais
Same pixels, fewer tokens. For user-facing markup: keeps the full design, expresses it densely with CSS vars, shorthand, fluid units.
Langue du texte source : anglais
Per-project persistent memory: save and recall durable facts across sessions as small frontmatter files, indexed in MEMORY.md.
Langue du texte source : anglais
Review a diff for over-engineering and verbosity. Terse delete-list of what to cut and the lines each saves. One-shot.
Langue du texte source : anglais