Not in the top 1,000 by GitHub stars
fraylabs/possible
See what AI made and the recipe behind it: exact prompts, skills, tools and steps. Search recipes, capture your own Claude Code or Codex session, publish from your repo.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/possible/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
613b612e092f → 0cc62238fc38
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → 613b612e092f
No earlier version was observed for comparison.
Verified commit 0cc62238fc38379cb3d909486e0d3df63716ce5d
git clone --filter=blob:none --no-checkout https://github.com/fraylabs/possible.git .hotskills/fraylabs-possible && git -C .hotskills/fraylabs-possible checkout --detach 0cc62238fc38379cb3d909486e0d3df63716ce5d
# Copy each selected skill directory from .hotskills/fraylabs-possible into .agents/skills/<skill-name>/Heat
1.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- possible
skills/possible
How it works
possible
When your agent uses it
Discover Outcomes and their disclosed recipes, then prepare a complete starting brief for a fresh agent. Also author and validate source-owned Outcomes for Possible.
What it loads into context
Frontmatter
34 tokensAlways available to the agent
SKILL.md
2,160 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Install the CLI
- Discover before writing
- Resolve consequential unknowns
- Prepare a complete starting brief
- Hand off once
- Author a completed Outcome
- Publish from the owner's source
- Local bookmarks
- Capture a finished session
Files
SKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesSKILL.mdcore10,756 bytesagents/openai.yamlasset240 bytes
Read SKILL.md
# Possible
Possible connects the user’s intended result with existing **Outcomes** and their
disclosed **recipes**: prompts, models, agents, pinned skills, references, tools
and ordered steps. Simple Outcomes may contain only a prompt.
An Outcome is precedent to inspect and remix, not a rigid workflow. Preserve useful creative freedom while giving a fresh agent the context, current methods, and concrete inputs it needs.
## Install the CLI
When the Possible MCP is unavailable, install the standalone CLI once:
```sh
curl -fsSL https://possible.sh/install.sh | shSkills included
- possible
Repository facts
- License
- MIT
- Created
- Jul 17, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 0
- Open issues
- 2
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 8 notes
skills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/possible/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 1 dangerous shell commandin 1 file: possible/SKILL.md:19
- 5 network referencesin 1 file: possible/SKILL.md:19
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 6 signals by file
skills/possible/SKILL.md
- Dangerous shell operationline 19
curl -fsSL https://possible.sh/install.sh | sh - Network accessline 19
curl -fsSL https://possible.sh/install.sh | sh - Network accessline 113
- a public GitHub repository; or - `https://publisher.example/.well-known/possible/outcomes.json`. - Network accessline 114
- `https://publisher.example/.well-known/possible/outcomes.json`. - Network accessline 119
possible publish [owner/repository | https://publisher.example] - Network accessline 120
possible add <owner/repository | https://publisher.example>
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Combined signals: 1 fact
- Passes content downloaded from possible.sh to an interpreterpossible/SKILL.md:19High confidence
Signal confidence: 6 facts
- Dangerous shell operation in code of the SKILL.mdpossible/SKILL.md:19High confidence
- Network access in code of the SKILL.mdpossible/SKILL.md:19High confidence
- Network access in prose of the SKILL.mdpossible/SKILL.md:113Low confidence
- Network access in prose of the SKILL.mdpossible/SKILL.md:114Low confidence
- Network access in code of the SKILL.mdpossible/SKILL.md:119High confidence
- Network access in code of the SKILL.mdpossible/SKILL.md:120High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/possible/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/possible/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/possible/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/possible/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/possible/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
